Upload folder using huggingface_hub
Browse files- README.md +9 -0
- config.json +34 -0
- merges.txt +0 -0
- onnx/model.onnx +3 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_int8.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
- preprocessor_config.json +27 -0
- quantize_config.json +18 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +29 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers.js
|
3 |
+
base_model:
|
4 |
+
- wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M
|
5 |
+
---
|
6 |
+
|
7 |
+
# TinyCLIP-ViT-8M-16-Text-3M-YFCC15M (ONNX)
|
8 |
+
|
9 |
+
This is an ONNX version of [wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M](https://huggingface.co/wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M",
|
4 |
+
"architectures": [
|
5 |
+
"CLIPModel"
|
6 |
+
],
|
7 |
+
"initializer_factor": 1.0,
|
8 |
+
"logit_scale_init_value": 2.6592,
|
9 |
+
"model_type": "clip",
|
10 |
+
"projection_dim": 512,
|
11 |
+
"text_config": {
|
12 |
+
"dropout": 0.0,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_size": 256,
|
15 |
+
"intermediate_size": 1024,
|
16 |
+
"model_type": "clip_text_model",
|
17 |
+
"num_attention_heads": 4,
|
18 |
+
"num_hidden_layers": 3,
|
19 |
+
"torch_dtype": "float32"
|
20 |
+
},
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.49.0",
|
23 |
+
"vision_config": {
|
24 |
+
"dropout": 0.0,
|
25 |
+
"hidden_act": "gelu",
|
26 |
+
"hidden_size": 256,
|
27 |
+
"intermediate_size": 1024,
|
28 |
+
"model_type": "clip_vision_model",
|
29 |
+
"num_attention_heads": 4,
|
30 |
+
"num_hidden_layers": 10,
|
31 |
+
"patch_size": 16,
|
32 |
+
"torch_dtype": "float32"
|
33 |
+
}
|
34 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a436651f4bebe3b31d9ae4e15bbac18837ed9180a1f656631cbea8d458dbcd6
|
3 |
+
size 94071688
|
onnx/model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28827c34781a2c51f556b03aa54df59451290d457ad2b71cbc3e0d10a92dc46c
|
3 |
+
size 58039360
|
onnx/model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b615f92f3c08534b88ea75c97f2f78c88ea13418d9c6a9298d19b82ae192964d
|
3 |
+
size 47180275
|
onnx/model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:844d1a46ab18acf50c989e541b12fe3b6dc7f8d6004725b4e992d142788e0600
|
3 |
+
size 24281512
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b79751d8e1f0c1a3acc16d01b65d6f0c5b32d1556f98db1f6ce3bf98a868684
|
3 |
+
size 58694084
|
onnx/model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84e1fff24a766765d80645971b7959f105ac7a24ee5e9e7c651232e86e4799d7
|
3 |
+
size 32118827
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10921310ddef06557ec1598d1260470a0a4db53f70ffe0deb60b946dcad6d27a
|
3 |
+
size 24281512
|
onnx/model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10921310ddef06557ec1598d1260470a0a4db53f70ffe0deb60b946dcad6d27a
|
3 |
+
size 24281512
|
preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "CLIPFeatureExtractor",
|
17 |
+
"image_std": [
|
18 |
+
0.26862954,
|
19 |
+
0.26130258,
|
20 |
+
0.27577711
|
21 |
+
],
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"shortest_edge": 224
|
26 |
+
}
|
27 |
+
}
|
quantize_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"modes": [
|
3 |
+
"fp16",
|
4 |
+
"q8",
|
5 |
+
"int8",
|
6 |
+
"uint8",
|
7 |
+
"q4",
|
8 |
+
"q4f16",
|
9 |
+
"bnb4"
|
10 |
+
],
|
11 |
+
"per_channel": true,
|
12 |
+
"reduce_range": true,
|
13 |
+
"block_size": null,
|
14 |
+
"is_symmetric": true,
|
15 |
+
"accuracy_level": null,
|
16 |
+
"quant_type": 1,
|
17 |
+
"op_block_list": null
|
18 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|startoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"49406": {
|
4 |
+
"content": "<|startoftext|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"49407": {
|
12 |
+
"content": "<|endoftext|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"bos_token": "<|startoftext|>",
|
21 |
+
"clean_up_tokenization_spaces": false,
|
22 |
+
"eos_token": "<|endoftext|>",
|
23 |
+
"extra_special_tokens": {},
|
24 |
+
"model_max_length": 1000000000000000019884624838656,
|
25 |
+
"pad_token": "<|endoftext|>",
|
26 |
+
"processor_class": "CLIPProcessor",
|
27 |
+
"tokenizer_class": "CLIPTokenizer",
|
28 |
+
"unk_token": "<|endoftext|>"
|
29 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|