Hugging Face's logo

Thouph
/
clip-vit-large-patch14-224-datacomp-hf

Zero-Shot Image Classification
Transformers
PyTorch
JAX
clip
Model card Files
xet
 Community
1
Thouph commited on
Commit
03e2bae
·
1 Parent(s): 473b81c

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +165 -0
  2. merges.txt +0 -0
  3. preprocessor_config.json +19 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +33 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "84c9828e63dc9a9351d1fe637c346d4c1c4db341",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "gelu",
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_factor": 1.0,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": false,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 77,
49
+ "min_length": 0,
50
+ "model_type": "clip_text_model",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "projection_dim": 512,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "transformers_version": "4.31.0",
82
+ "typical_p": 1.0,
83
+ "use_bfloat16": false,
84
+ "vocab_size": 49408
85
+ },
86
+ "torch_dtype": "float32",
87
+ "transformers_version": null,
88
+ "vision_config": {
89
+ "_name_or_path": "",
90
+ "add_cross_attention": false,
91
+ "architectures": null,
92
+ "attention_dropout": 0.0,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": null,
96
+ "chunk_size_feed_forward": 0,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "diversity_penalty": 0.0,
100
+ "do_sample": false,
101
+ "early_stopping": false,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "eos_token_id": null,
104
+ "exponential_decay_length_penalty": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "gelu",
109
+ "hidden_size": 1024,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "image_size": 224,
115
+ "initializer_factor": 1.0,
116
+ "initializer_range": 0.02,
117
+ "intermediate_size": 4096,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "layer_norm_eps": 1e-05,
125
+ "length_penalty": 1.0,
126
+ "max_length": 20,
127
+ "min_length": 0,
128
+ "model_type": "clip_vision_model",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 16,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_channels": 3,
134
+ "num_hidden_layers": 24,
135
+ "num_return_sequences": 1,
136
+ "output_attentions": false,
137
+ "output_hidden_states": false,
138
+ "output_scores": false,
139
+ "pad_token_id": null,
140
+ "patch_size": 14,
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "projection_dim": 512,
144
+ "pruned_heads": {},
145
+ "remove_invalid_values": false,
146
+ "repetition_penalty": 1.0,
147
+ "return_dict": true,
148
+ "return_dict_in_generate": false,
149
+ "sep_token_id": null,
150
+ "suppress_tokens": null,
151
+ "task_specific_params": null,
152
+ "temperature": 1.0,
153
+ "tf_legacy_loss": false,
154
+ "tie_encoder_decoder": false,
155
+ "tie_word_embeddings": true,
156
+ "tokenizer_class": null,
157
+ "top_k": 50,
158
+ "top_p": 1.0,
159
+ "torch_dtype": null,
160
+ "torchscript": false,
161
+ "transformers_version": "4.31.0",
162
+ "typical_p": 1.0,
163
+ "use_bfloat16": false
164
+ }
165
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 224
19
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb5fe498f92dd974706224743f7a7ac3fb5ff36a1e35b313e1a6873f14e4d21
3
+ size 1710660997
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff