Upload BlipForConditionalGeneration

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Salesforce/blip-image-captioning-base",
   "architectures": [
     "BlipForConditionalGeneration"
   ],
@@ -11,44 +12,20 @@
   "projection_dim": 512,
   "text_config": {
     "_attn_implementation_autoset": true,
-    "attention_probs_dropout_prob": 0.0,
-    "encoder_hidden_size": 1024,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.0,
-    "hidden_size": 768,
     "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "label_smoothing": 0.0,
-    "layer_norm_eps": 1e-12,
-    "max_position_embeddings": 512,
     "model_type": "blip_text_model",
     "num_attention_heads": 12,
-    "num_hidden_layers": 12,
-    "projection_dim": 768,
-    "torch_dtype": "float32",
-    "use_cache": true,
-    "vocab_size": 30524
+    "torch_dtype": "float32"
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.49.0",
   "vision_config": {
     "_attn_implementation_autoset": true,
-    "attention_dropout": 0.0,
     "dropout": 0.0,
-    "hidden_act": "gelu",
-    "hidden_size": 1024,
-    "image_size": 384,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "layer_norm_eps": 1e-05,
     "model_type": "blip_vision_model",
-    "num_attention_heads": 16,
     "num_channels": 3,
-    "num_hidden_layers": 24,
-    "patch_size": 16,
-    "projection_dim": 512,
     "torch_dtype": "float32"
   }
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 30522,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.49.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c3b1652dc8f86c76f28d5e5a4e0c37843a2a5b1d276ca415da7a90d2a87a31
-size 1879010480
+oid sha256:a15d7be1e58f6164212464b637f70c82260908ff005bb9964f988e4d523ec70c
+size 989717056