Upload Idefics3ForConditionalGeneration

config.json

@@ -2,6 +2,7 @@
   "architectures": [
     "Idefics3ForConditionalGeneration"
   ],
+  "dtype": "bfloat16",
   "image_token_id": 128257,
   "model_type": "idefics3",
   "pad_token_id": 128002,
@@ -19,6 +20,7 @@
       "AutoModelForCausalLM": "modeling_idefics3.Idefics3ForVisionText2Text"
     },
     "bos_token_id": 128000,
+    "dtype": "bfloat16",
     "eos_token_id": [
       128001,
       128008,
@@ -29,6 +31,7 @@
     "hidden_size": 16,
     "initializer_range": 0.02,
     "intermediate_size": 14336,
+    "layer_types": null,
     "max_position_embeddings": 131072,
     "mlp_bias": false,
     "model_type": "llama",
@@ -120,17 +123,16 @@
       "rope_type": "llama3"
     },
     "rope_theta": 500000.0,
-    "torch_dtype": "bfloat16",
     "use_cache": true,
     "use_resampler": false,
     "vocab_size": 128259
   },
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.56.0.dev0",
+  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "vision_config": {
     "attention_dropout": 0.0,
+    "embed_dim": 32,
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 16,
     "image_size": 364,

generation_config.json

@@ -7,5 +7,5 @@
     128009
   ],
   "pad_token_id": 128002,
-  "transformers_version": "4.56.0.dev0"
+  "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a661eb4c15afccb9c68e712860b057ce8fdf886c5a0ee655c130a44d406dfc07
+oid sha256:b27ea2b8b1c0a8ec9a57b425e85c05f8832cfcf202d0945a879ffd675143c3db
 size 11682096