shunxing1234 commited on
Commit
b989a7b
1 Parent(s): f372c04

Upload 6 files

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "4d06f38b304fc2a331d9f3eab77a542afafc4ffb",
3
+ "_name_or_path": "BAAI/AltCLIP",
4
+ "architectures": [
5
+ "AltCLIPModel"
6
+ ],
7
+ "direct_kd": false,
8
+ "initializer_factor": 1.0,
9
+ "logit_scale_init_value": 2.6592,
10
+ "model_type": "altclip",
11
+ "num_layers": 3,
12
+ "projection_dim": 768,
13
+ "text_config": {
14
+ "_name_or_path": "",
15
+ "add_cross_attention": false,
16
+ "architectures": null,
17
+ "attention_probs_dropout_prob": 0.1,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": 0,
21
+ "chunk_size_feed_forward": 0,
22
+ "classifier_dropout": null,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 2,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "hidden_act": "gelu",
35
+ "hidden_dropout_prob": 0.1,
36
+ "hidden_size": 1024,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_factor": 0.02,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 4096,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "layer_norm_eps": 1e-05,
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 514,
54
+ "min_length": 0,
55
+ "model_type": "altclip_text_model",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 16,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 24,
61
+ "num_return_sequences": 1,
62
+ "output_attentions": false,
63
+ "output_hidden_states": false,
64
+ "output_scores": false,
65
+ "pad_token_id": 1,
66
+ "pooler_fn": "cls",
67
+ "position_embedding_type": "absolute",
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "project_dim": 768,
71
+ "pruned_heads": {},
72
+ "remove_invalid_values": false,
73
+ "repetition_penalty": 1.0,
74
+ "return_dict": true,
75
+ "return_dict_in_generate": false,
76
+ "sep_token_id": null,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": null,
79
+ "temperature": 1.0,
80
+ "tf_legacy_loss": false,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": true,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": null,
87
+ "torchscript": false,
88
+ "transformers_version": "4.26.0.dev0",
89
+ "type_vocab_size": 1,
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": true,
93
+ "vocab_size": 250002
94
+ },
95
+ "text_config_dict": {
96
+ "hidden_size": 1024,
97
+ "intermediate_size": 4096,
98
+ "num_attention_heads": 16,
99
+ "num_hidden_layers": 24
100
+ },
101
+ "text_model_name": null,
102
+ "torch_dtype": "float32",
103
+ "transformers_version": null,
104
+ "vision_config": {
105
+ "_name_or_path": "",
106
+ "add_cross_attention": false,
107
+ "architectures": null,
108
+ "attention_dropout": 0.0,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": null,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": null,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "dropout": 0.0,
118
+ "early_stopping": false,
119
+ "encoder_no_repeat_ngram_size": 0,
120
+ "eos_token_id": null,
121
+ "exponential_decay_length_penalty": null,
122
+ "finetuning_task": null,
123
+ "forced_bos_token_id": null,
124
+ "forced_eos_token_id": null,
125
+ "hidden_act": "quick_gelu",
126
+ "hidden_size": 1024,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "image_size": 224,
132
+ "initializer_factor": 1.0,
133
+ "initializer_range": 0.02,
134
+ "intermediate_size": 4096,
135
+ "is_decoder": false,
136
+ "is_encoder_decoder": false,
137
+ "label2id": {
138
+ "LABEL_0": 0,
139
+ "LABEL_1": 1
140
+ },
141
+ "layer_norm_eps": 1e-05,
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "min_length": 0,
145
+ "model_type": "altclip_vision_model",
146
+ "no_repeat_ngram_size": 0,
147
+ "num_attention_heads": 16,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_channels": 3,
151
+ "num_hidden_layers": 24,
152
+ "num_return_sequences": 1,
153
+ "output_attentions": false,
154
+ "output_hidden_states": false,
155
+ "output_scores": false,
156
+ "pad_token_id": null,
157
+ "patch_size": 14,
158
+ "prefix": null,
159
+ "problem_type": null,
160
+ "projection_dim": 512,
161
+ "pruned_heads": {},
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict": true,
165
+ "return_dict_in_generate": false,
166
+ "sep_token_id": null,
167
+ "suppress_tokens": null,
168
+ "task_specific_params": null,
169
+ "temperature": 1.0,
170
+ "tf_legacy_loss": false,
171
+ "tie_encoder_decoder": false,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": null,
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": null,
177
+ "torchscript": false,
178
+ "transformers_version": "4.26.0.dev0",
179
+ "typical_p": 1.0,
180
+ "use_bfloat16": false
181
+ },
182
+ "vision_config_dict": {
183
+ "hidden_size": 1024,
184
+ "intermediate_size": 4096,
185
+ "num_attention_heads": 16,
186
+ "num_hidden_layers": 24,
187
+ "patch_size": 14
188
+ },
189
+ "vision_model_name": null
190
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "processor_class": "AltCLIPProcessor",
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 224
28
+ }
29
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3788bb2f349135f2ad2e2b10dff3cee7f23fab906a5fbdadf20bc963b05b4c
3
+ size 17098080
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "BAAI/AltCLIP",
15
+ "pad_token": "<pad>",
16
+ "processor_class": "AltCLIPProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }