sayantan47 commited on
Commit
a11a1ab
·
verified ·
1 Parent(s): cdc58db

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
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
+ "eos_token_id": 2,
15
+ "hidden_act": "quick_gelu",
16
+ "hidden_size": 512,
17
+ "initializer_factor": 1.0,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 2048,
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 77,
22
+ "model_type": "clip_text_model",
23
+ "num_attention_heads": 8,
24
+ "num_hidden_layers": 12,
25
+ "projection_dim": 512,
26
+ "torch_dtype": "float32",
27
+ "vocab_size": 49408
28
+ },
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.51.3",
31
+ "vision_config": {
32
+ "attention_dropout": 0.0,
33
+ "dropout": 0.0,
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
+ "torch_dtype": "float32"
48
+ }
49
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3796fadb6cb16ad79ff34c0873d29cd9ce1578ec621286c13072c6f1014346
3
+ size 605593696
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": "CLIPImageProcessor",
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
+ }
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 77,
28
+ "pad_token": "<|endoftext|>",
29
+ "processor_class": "CLIPProcessor",
30
+ "tokenizer_class": "CLIPTokenizer",
31
+ "unk_token": "<|endoftext|>"
32
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff