{ "metadata": { "total_size": 8536919040 }, "weight_map": { "lm_head.weight": "model-00002-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors" } }