valhalla commited on
Commit
25b80ac
1 Parent(s): 856a6f2
config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPModel"
4
+ ],
5
+ "initializer_factor": 1.0,
6
+ "model_type": "clip",
7
+ "projection_dim": 512,
8
+ "text_config": {
9
+ "_name_or_path": "",
10
+ "add_cross_attention": false,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "dropout": 0.0,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 2,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "quick_gelu",
28
+ "hidden_size": 512,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_factor": 1.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 2048,
36
+ "is_decoder": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 77,
46
+ "min_length": 0,
47
+ "model_type": "clip_text_model",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 8,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "task_specific_params": null,
67
+ "temperature": 1.0,
68
+ "tie_encoder_decoder": false,
69
+ "tie_word_embeddings": true,
70
+ "tokenizer_class": null,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "torchscript": false,
74
+ "transformers_version": "4.6.0.dev0",
75
+ "use_bfloat16": false,
76
+ "vocab_size": 49408
77
+ },
78
+ "text_config_dict": null,
79
+ "transformers_version": null,
80
+ "vision_config": {
81
+ "_name_or_path": "",
82
+ "add_cross_attention": false,
83
+ "architectures": null,
84
+ "attention_dropout": 0.0,
85
+ "bad_words_ids": null,
86
+ "bos_token_id": null,
87
+ "chunk_size_feed_forward": 0,
88
+ "decoder_start_token_id": null,
89
+ "diversity_penalty": 0.0,
90
+ "do_sample": false,
91
+ "dropout": 0.0,
92
+ "early_stopping": false,
93
+ "encoder_no_repeat_ngram_size": 0,
94
+ "eos_token_id": null,
95
+ "finetuning_task": null,
96
+ "forced_bos_token_id": null,
97
+ "forced_eos_token_id": null,
98
+ "gradient_checkpointing": false,
99
+ "hidden_act": "quick_gelu",
100
+ "hidden_size": 768,
101
+ "id2label": {
102
+ "0": "LABEL_0",
103
+ "1": "LABEL_1"
104
+ },
105
+ "image_size": 224,
106
+ "initializer_factor": 1.0,
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 3072,
109
+ "is_decoder": false,
110
+ "is_encoder_decoder": false,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1
114
+ },
115
+ "layer_norm_eps": 1e-05,
116
+ "length_penalty": 1.0,
117
+ "max_length": 20,
118
+ "min_length": 0,
119
+ "model_type": "clip_vision_model",
120
+ "no_repeat_ngram_size": 0,
121
+ "num_attention_heads": 12,
122
+ "num_beam_groups": 1,
123
+ "num_beams": 1,
124
+ "num_hidden_layers": 12,
125
+ "num_return_sequences": 1,
126
+ "output_attentions": false,
127
+ "output_hidden_states": false,
128
+ "output_scores": false,
129
+ "pad_token_id": null,
130
+ "patch_size": 32,
131
+ "prefix": null,
132
+ "problem_type": null,
133
+ "pruned_heads": {},
134
+ "remove_invalid_values": false,
135
+ "repetition_penalty": 1.0,
136
+ "return_dict": true,
137
+ "return_dict_in_generate": false,
138
+ "sep_token_id": null,
139
+ "task_specific_params": null,
140
+ "temperature": 1.0,
141
+ "tie_encoder_decoder": false,
142
+ "tie_word_embeddings": true,
143
+ "tokenizer_class": null,
144
+ "top_k": 50,
145
+ "top_p": 1.0,
146
+ "torchscript": false,
147
+ "transformers_version": "4.6.0.dev0",
148
+ "use_bfloat16": false
149
+ },
150
+ "vision_config_dict": null
151
+ }
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:a63082132ba4f97a80bea76823f544493bffa8082296d62d71581a4feff1576f
3
+ size 605247071
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "do_lower_case": true, "name_or_path": "./clip_ViT_B_32/"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff