Upload folder using huggingface_hub
Browse files- 0_CLIPModel/config.json +48 -0
- 0_CLIPModel/merges.txt +0 -0
- 0_CLIPModel/model.safetensors +3 -0
- 0_CLIPModel/model_quantized.onnx +3 -0
- 0_CLIPModel/ort_config.json +33 -0
- 0_CLIPModel/preprocessor_config.json +28 -0
- 0_CLIPModel/special_tokens_map.json +30 -0
- 0_CLIPModel/tokenizer.json +0 -0
- 0_CLIPModel/tokenizer_config.json +36 -0
- 0_CLIPModel/vocab.json +0 -0
- config_sentence_transformers.json +9 -0
- modules.json +8 -0
0_CLIPModel/config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPModel"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"dtype": "float32",
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"hidden_act": "quick_gelu",
|
| 17 |
+
"hidden_size": 512,
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 2048,
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 77,
|
| 23 |
+
"model_type": "clip_text_model",
|
| 24 |
+
"num_attention_heads": 8,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"projection_dim": 512,
|
| 27 |
+
"vocab_size": 49408
|
| 28 |
+
},
|
| 29 |
+
"transformers_version": "4.57.6",
|
| 30 |
+
"vision_config": {
|
| 31 |
+
"attention_dropout": 0.0,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dtype": "float32",
|
| 34 |
+
"hidden_act": "quick_gelu",
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_factor": 1.0,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 3072,
|
| 40 |
+
"layer_norm_eps": 1e-05,
|
| 41 |
+
"model_type": "clip_vision_model",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_channels": 3,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"patch_size": 32,
|
| 46 |
+
"projection_dim": 512
|
| 47 |
+
}
|
| 48 |
+
}
|
0_CLIPModel/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
0_CLIPModel/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a384c9dc38d022f210c2ef055d317400bf2e9811af1da6bab39bd0e0bc8888f9
|
| 3 |
+
size 605156676
|
0_CLIPModel/model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7d98d9d4fce473fb6ece48ef06aa4ade4a60915a54a7a48b68aa73bac289dd4
|
| 3 |
+
size 152763031
|
0_CLIPModel/ort_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"one_external_file": true,
|
| 3 |
+
"opset": null,
|
| 4 |
+
"optimization": {},
|
| 5 |
+
"quantization": {
|
| 6 |
+
"activations_dtype": "QUInt8",
|
| 7 |
+
"activations_symmetric": false,
|
| 8 |
+
"format": "QOperator",
|
| 9 |
+
"is_static": false,
|
| 10 |
+
"mode": "IntegerOps",
|
| 11 |
+
"nodes_to_exclude": [],
|
| 12 |
+
"nodes_to_quantize": [],
|
| 13 |
+
"operators_to_quantize": [
|
| 14 |
+
"Conv",
|
| 15 |
+
"MatMul",
|
| 16 |
+
"Attention",
|
| 17 |
+
"LSTM",
|
| 18 |
+
"Gather",
|
| 19 |
+
"Transpose",
|
| 20 |
+
"EmbedLayerNormalization"
|
| 21 |
+
],
|
| 22 |
+
"per_channel": false,
|
| 23 |
+
"qdq_add_pair_to_weight": false,
|
| 24 |
+
"qdq_dedicated_pair": false,
|
| 25 |
+
"qdq_op_type_per_channel_support_to_axis": {
|
| 26 |
+
"MatMul": 1
|
| 27 |
+
},
|
| 28 |
+
"reduce_range": false,
|
| 29 |
+
"weights_dtype": "QUInt8",
|
| 30 |
+
"weights_symmetric": true
|
| 31 |
+
},
|
| 32 |
+
"use_external_data_format": false
|
| 33 |
+
}
|
0_CLIPModel/preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"processor_class": "CLIPProcessor",
|
| 23 |
+
"resample": 3,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"shortest_edge": 224
|
| 27 |
+
}
|
| 28 |
+
}
|
0_CLIPModel/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
0_CLIPModel/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
0_CLIPModel/tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"49406": {
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49407": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|startoftext|>",
|
| 22 |
+
"clean_up_tokenization_spaces": false,
|
| 23 |
+
"do_lower_case": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"extra_special_tokens": {},
|
| 27 |
+
"max_length": null,
|
| 28 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 29 |
+
"pad_to_multiple_of": null,
|
| 30 |
+
"pad_token": "<|endoftext|>",
|
| 31 |
+
"pad_token_type_id": 0,
|
| 32 |
+
"padding_side": "right",
|
| 33 |
+
"processor_class": "CLIPProcessor",
|
| 34 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 35 |
+
"unk_token": "<|endoftext|>"
|
| 36 |
+
}
|
0_CLIPModel/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "2.7.0",
|
| 4 |
+
"transformers": "4.57.6",
|
| 5 |
+
"pytorch": "2.11.0+cu128"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null
|
| 9 |
+
}
|
modules.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "0_CLIPModel",
|
| 6 |
+
"type": "sentence_transformers.models.CLIPModel"
|
| 7 |
+
}
|
| 8 |
+
]
|