Upload BlipForConditionalGeneration
Browse files- config.json +31 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Salesforce/blip-image-captioning-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BlipForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"image_text_hidden_size": 256,
|
| 7 |
+
"initializer_factor": 1.0,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"logit_scale_init_value": 2.6592,
|
| 10 |
+
"model_type": "blip",
|
| 11 |
+
"projection_dim": 512,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"encoder_hidden_size": 1024,
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"model_type": "blip_text_model",
|
| 16 |
+
"num_attention_heads": 12
|
| 17 |
+
},
|
| 18 |
+
"torch_dtype": "float32",
|
| 19 |
+
"transformers_version": "4.33.0.dev0",
|
| 20 |
+
"vision_config": {
|
| 21 |
+
"dropout": 0.0,
|
| 22 |
+
"hidden_size": 1024,
|
| 23 |
+
"initializer_factor": 1.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 4096,
|
| 26 |
+
"model_type": "blip_vision_model",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_channels": 3,
|
| 29 |
+
"num_hidden_layers": 24
|
| 30 |
+
}
|
| 31 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb7a2101222c6e686cf49c87f0e226f07a654fc2e600df3bf7a84b77c02a18eb
|
| 3 |
+
size 1879148141
|