Training in progress, step 213

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Salesforce/blip-image-captioning-large",
+  "_name_or_path": "Salesforce/blip-image-captioning-base",
   "architectures": [
     "BlipForConditionalGeneration"
   ],
@@ -13,7 +13,6 @@
   "pad_token_id": 0,
   "projection_dim": 512,
   "text_config": {
-    "encoder_hidden_size": 1024,
     "initializer_factor": 1.0,
     "model_type": "blip_text_model",
     "num_attention_heads": 12
@@ -22,13 +21,9 @@
   "transformers_version": "4.36.2",
   "vision_config": {
     "dropout": 0.0,
-    "hidden_size": 1024,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 4096,
     "model_type": "blip_vision_model",
-    "num_attention_heads": 16,
-    "num_channels": 3,
-    "num_hidden_layers": 24
+    "num_channels": 3
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ab47f62c8880fbc55f34d3b6c79726076910b5445a7c7d735603a9093d25a8
-size 1879010480
+oid sha256:1fa190fca443948896af38e5365ea398562c4761fb0540c155f1c0e6092dd74f
+size 989717056