Alex Shonenkov commited on
Commit
738da4f
1 Parent(s): 28f2302

add b32 checkpoint

Browse files
ruclip-vit-base-patch32-v5/bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26db7928d1a022215fc5a1948c46d17c8e39e471b4d0f8b3d1edfd91c7c62571
3
+ size 747907
ruclip-vit-base-patch32-v5/config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.8.2",
75
+ "use_bfloat16": false,
76
+ "vocab_size": 49408
77
+ },
78
+ "text_config_dict": null,
79
+ "torch_dtype": "float32",
80
+ "transformers_version": null,
81
+ "vision_config": {
82
+ "_name_or_path": "",
83
+ "add_cross_attention": false,
84
+ "architectures": null,
85
+ "attention_dropout": 0.0,
86
+ "bad_words_ids": null,
87
+ "bos_token_id": null,
88
+ "chunk_size_feed_forward": 0,
89
+ "decoder_start_token_id": null,
90
+ "diversity_penalty": 0.0,
91
+ "do_sample": false,
92
+ "dropout": 0.0,
93
+ "early_stopping": false,
94
+ "encoder_no_repeat_ngram_size": 0,
95
+ "eos_token_id": null,
96
+ "finetuning_task": null,
97
+ "forced_bos_token_id": null,
98
+ "forced_eos_token_id": null,
99
+ "gradient_checkpointing": false,
100
+ "hidden_act": "quick_gelu",
101
+ "hidden_size": 768,
102
+ "id2label": {
103
+ "0": "LABEL_0",
104
+ "1": "LABEL_1"
105
+ },
106
+ "image_size": 224,
107
+ "initializer_factor": 1.0,
108
+ "initializer_range": 0.02,
109
+ "intermediate_size": 3072,
110
+ "is_decoder": false,
111
+ "is_encoder_decoder": false,
112
+ "label2id": {
113
+ "LABEL_0": 0,
114
+ "LABEL_1": 1
115
+ },
116
+ "layer_norm_eps": 1e-05,
117
+ "length_penalty": 1.0,
118
+ "max_length": 20,
119
+ "min_length": 0,
120
+ "model_type": "clip_vision_model",
121
+ "no_repeat_ngram_size": 0,
122
+ "num_attention_heads": 12,
123
+ "num_beam_groups": 1,
124
+ "num_beams": 1,
125
+ "num_hidden_layers": 12,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": null,
131
+ "patch_size": 32,
132
+ "prefix": null,
133
+ "problem_type": null,
134
+ "pruned_heads": {},
135
+ "remove_invalid_values": false,
136
+ "repetition_penalty": 1.0,
137
+ "return_dict": true,
138
+ "return_dict_in_generate": false,
139
+ "sep_token_id": null,
140
+ "task_specific_params": null,
141
+ "temperature": 1.0,
142
+ "tie_encoder_decoder": false,
143
+ "tie_word_embeddings": true,
144
+ "tokenizer_class": null,
145
+ "top_k": 50,
146
+ "top_p": 1.0,
147
+ "torchscript": false,
148
+ "transformers_version": "4.8.2",
149
+ "use_bfloat16": false
150
+ },
151
+ "vision_config_dict": {
152
+ "patch_size": 32
153
+ },
154
+ "vocab_size": 49408,
155
+ "mean": [0.48145466, 0.4578275, 0.40821073],
156
+ "std": [0.26862954, 0.26130258, 0.27577711]
157
+ }
ruclip-vit-base-patch32-v5/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15a4810e6d64fa4f1a374e109d2eba933f3624a5fb7e20cf9794aca6007b567
3
+ size 605266175