Upload 5 files
Browse files- config.json +52 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- preprocessor_config.json +17 -0
- tokenizer.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BlipForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 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 |
+
"attention_probs_dropout_prob": 0.0,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"encoder_hidden_size": 768,
|
| 17 |
+
"hidden_act": "gelu",
|
| 18 |
+
"hidden_dropout_prob": 0.0,
|
| 19 |
+
"hidden_size": 768,
|
| 20 |
+
"initializer_factor": 1.0,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label_smoothing": 0.0,
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "blip_text_model",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"projection_dim": 768,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 30524
|
| 32 |
+
},
|
| 33 |
+
"transformers_version": "4.57.3",
|
| 34 |
+
"vision_config": {
|
| 35 |
+
"attention_dropout": 0.0,
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"dtype": "float32",
|
| 38 |
+
"hidden_act": "gelu",
|
| 39 |
+
"hidden_size": 768,
|
| 40 |
+
"image_size": 384,
|
| 41 |
+
"initializer_factor": 1.0,
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 3072,
|
| 44 |
+
"layer_norm_eps": 1e-05,
|
| 45 |
+
"model_type": "blip_vision_model",
|
| 46 |
+
"num_attention_heads": 12,
|
| 47 |
+
"num_channels": 3,
|
| 48 |
+
"num_hidden_layers": 12,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"projection_dim": 512
|
| 51 |
+
}
|
| 52 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 30522,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.57.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6586e1cbdea87452fef7bef0230277f38d0519a81fa724d804e2d01999fd16b3
|
| 3 |
+
size 895947208
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"image_mean": [
|
| 5 |
+
0.48145466,
|
| 6 |
+
0.4578275,
|
| 7 |
+
0.40821073
|
| 8 |
+
],
|
| 9 |
+
"image_processor_type": "BlipImageProcessor",
|
| 10 |
+
"image_std": [
|
| 11 |
+
0.26862954,
|
| 12 |
+
0.26130258,
|
| 13 |
+
0.27577711
|
| 14 |
+
],
|
| 15 |
+
"processor_class": "BlipProcessor",
|
| 16 |
+
"size": 384
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|