Training in progress, step 500

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "image_token_index": null,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "_attn_implementation_autoset": true,
+    "encoder_hidden_size": 1024,
+    "hidden_size": 1024,
+    "model_type": "blip_2_qformer",
+    "num_attention_heads": 16
+  },
+  "text_config": {
+    "model_type": "opt"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "hidden_size": 1024,
+    "image_size": 112,
+    "model_type": "blip_2_vision_model",
+    "num_hidden_layers": 12,
+    "patch_size": 16
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709154f17a806a3147ac6cf094855bf65202fec899d591ce0a2bbcc6707c2a41
+size 1918449256

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4639fc1381b0d18c185199da102182be2817548153862c3b6c85626e542b3622
+size 5368