feat: Add config.json for AutoModelForCausalLM support

config.json

@@ -1,22 +1,25 @@
 {
-  "architectures": [
-    "Max2ForCausalLM"
-  ],
-  "model_type": "max2",
-  "model_name": "max2-nano",
-  "hidden_size": 768,
-  "intermediate_size": 2048,
+  "architectures": ["MiniMindForCausalLM"],
+  "auto_map": {
+    "AutoConfig": "configuration_minimind.MiniMindConfig",
+    "AutoModelForCausalLM": "modeling_minimind.MiniMindForCausalLM"
+  },
+  "model_type": "minimind",
+  "vocab_size": 102400,
+  "hidden_size": 1024,
+  "intermediate_size": 2816,
   "num_hidden_layers": 12,
-  "num_attention_heads": 12,
-  "num_key_value_heads": 3,
-  "vocab_size": 32000,
-  "max_position_embeddings": 4096,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 4,
+  "max_position_embeddings": 32768,
+  "rms_norm_eps": 1e-6,
   "rope_theta": 10000.0,
-  "use_moe": true,
-  "num_experts": 4,
-  "num_experts_per_tok": 1,
-  "expert_hidden_size": 512,
-  "rms_norm_eps": 1e-06,
-  "torch_dtype": "float16",
+  "num_experts": 8,
+  "num_experts_per_token": 2,
+  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
   "transformers_version": "4.40.0"
-}
+}