Training in progress, step 213

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Salesforce/blip-image-captioning-large",
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "decoder_start_token_id": 101,
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "logit_scale_init_value": 2.6592,
+  "max_length": 100,
+  "model_type": "blip",
+  "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
+  },
+  "torch_dtype": "float32",
+  "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
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99091edca77dd29ba5d2917818db5e3a35f42eebd1e09c0cd847c3ba743b3cf5
+size 1879010480

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae17099adb07f504027d1b584b89b4fec6f7b01e03f6fcde1c3e82ca799ebe9
+size 4664