Upload 5 files

This model is a fine-tuned version of Salesforce/blip-image-captioning-base on a custom dataset.

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Salesforce/blip-image-captioning-base",
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "label_smoothing": 0.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "initializer_factor": 1.0,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "model_type": "blip_vision_model",
+    "num_channels": 3
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30522,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4465cbd71678ee874cff884a282e2144bf56e85e8175574305365911f6456876
+size 989717056

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "BlipImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "BlipProcessor",
+  "size": 384
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462d7f4d862fbaa5bb5f6c91c0b40a0276f2a1d15272e24f39357f5b50f7940e
+size 5240