Upload BlipForConditionalGeneration
Browse files- config.json +29 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "noamrot/FuseCap_Image_Captioning",
|
3 |
+
"architectures": [
|
4 |
+
"BlipForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"image_text_hidden_size": 256,
|
7 |
+
"initializer_factor": 1.0,
|
8 |
+
"initializer_range": 0.02,
|
9 |
+
"label_smoothing": 0.0,
|
10 |
+
"logit_scale_init_value": 2.6592,
|
11 |
+
"model_type": "blip",
|
12 |
+
"projection_dim": 512,
|
13 |
+
"text_config": {
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"max_length": 60,
|
16 |
+
"model_type": "blip_text_model",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_beams": 3
|
19 |
+
},
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.40.2",
|
22 |
+
"vision_config": {
|
23 |
+
"dropout": 0.0,
|
24 |
+
"initializer_factor": 1.0,
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"model_type": "blip_vision_model",
|
27 |
+
"num_channels": 3
|
28 |
+
}
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 30522,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 60,
|
6 |
+
"num_beams": 3,
|
7 |
+
"pad_token_id": 0,
|
8 |
+
"transformers_version": "4.40.2"
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e219a849ae3602c56a07b47d62c85f733b2a30ff9a1a5e8d715fba50525c534
|
3 |
+
size 989717056
|