hfl
/

ziqingyang commited on
Commit
6ca56c3
1 Parent(s): ee72412

Upload 6 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "attention_probs_dropout_prob": 0.1,
4
+ "classifier_dropout": null,
5
+ "hidden_act": "gelu",
6
+ "hidden_dropout_prob": 0.1,
7
+ "hidden_size": 768,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 3072,
10
+ "layer_norm_eps": 1e-12,
11
+ "model_type": "vle",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 6,
14
+ "num_token_types": 2,
15
+ "text_config": {
16
+ "_name_or_path": "",
17
+ "add_cross_attention": false,
18
+ "architectures": null,
19
+ "attention_probs_dropout_prob": 0.1,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": null,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "eos_token_id": null,
31
+ "exponential_decay_length_penalty": null,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "hidden_act": "gelu",
36
+ "hidden_dropout_prob": 0.1,
37
+ "hidden_size": 768,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 3072,
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-07,
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 512,
54
+ "max_relative_positions": -1,
55
+ "min_length": 0,
56
+ "model_type": "deberta-v2",
57
+ "no_repeat_ngram_size": 0,
58
+ "norm_rel_ebd": "layer_norm",
59
+ "num_attention_heads": 12,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_hidden_layers": 12,
63
+ "num_return_sequences": 1,
64
+ "output_attentions": false,
65
+ "output_hidden_states": false,
66
+ "output_scores": false,
67
+ "pad_token_id": 0,
68
+ "pooler_dropout": 0,
69
+ "pooler_hidden_act": "gelu",
70
+ "pooler_hidden_size": 768,
71
+ "pos_att_type": [
72
+ "p2c",
73
+ "c2p"
74
+ ],
75
+ "position_biased_input": false,
76
+ "position_buckets": 256,
77
+ "prefix": null,
78
+ "problem_type": null,
79
+ "pruned_heads": {},
80
+ "relative_attention": true,
81
+ "remove_invalid_values": false,
82
+ "repetition_penalty": 1.0,
83
+ "return_dict": true,
84
+ "return_dict_in_generate": false,
85
+ "sep_token_id": null,
86
+ "share_att_key": true,
87
+ "suppress_tokens": null,
88
+ "task_specific_params": null,
89
+ "temperature": 1.0,
90
+ "tf_legacy_loss": false,
91
+ "tie_encoder_decoder": false,
92
+ "tie_word_embeddings": true,
93
+ "tokenizer_class": null,
94
+ "top_k": 50,
95
+ "top_p": 1.0,
96
+ "torch_dtype": null,
97
+ "torchscript": false,
98
+ "transformers_version": "4.26.0",
99
+ "type_vocab_size": 0,
100
+ "typical_p": 1.0,
101
+ "use_bfloat16": false,
102
+ "vocab_size": 128100
103
+ },
104
+ "transformers_version": null,
105
+ "vision_config": {
106
+ "_name_or_path": "",
107
+ "add_cross_attention": false,
108
+ "architectures": null,
109
+ "attention_dropout": 0.0,
110
+ "bad_words_ids": null,
111
+ "begin_suppress_tokens": null,
112
+ "bos_token_id": null,
113
+ "chunk_size_feed_forward": 0,
114
+ "cross_attention_hidden_size": null,
115
+ "decoder_start_token_id": null,
116
+ "diversity_penalty": 0.0,
117
+ "do_sample": false,
118
+ "dropout": 0.0,
119
+ "early_stopping": false,
120
+ "encoder_no_repeat_ngram_size": 0,
121
+ "eos_token_id": null,
122
+ "exponential_decay_length_penalty": null,
123
+ "finetuning_task": null,
124
+ "forced_bos_token_id": null,
125
+ "forced_eos_token_id": null,
126
+ "hidden_act": "quick_gelu",
127
+ "hidden_size": 768,
128
+ "id2label": {
129
+ "0": "LABEL_0",
130
+ "1": "LABEL_1"
131
+ },
132
+ "image_size": 224,
133
+ "initializer_factor": 1.0,
134
+ "initializer_range": 0.02,
135
+ "intermediate_size": 3072,
136
+ "is_decoder": false,
137
+ "is_encoder_decoder": false,
138
+ "label2id": {
139
+ "LABEL_0": 0,
140
+ "LABEL_1": 1
141
+ },
142
+ "layer_norm_eps": 1e-05,
143
+ "length_penalty": 1.0,
144
+ "max_length": 20,
145
+ "min_length": 0,
146
+ "model_type": "clip_vision_model",
147
+ "no_repeat_ngram_size": 0,
148
+ "num_attention_heads": 12,
149
+ "num_beam_groups": 1,
150
+ "num_beams": 1,
151
+ "num_channels": 3,
152
+ "num_hidden_layers": 11,
153
+ "num_return_sequences": 1,
154
+ "output_attentions": false,
155
+ "output_hidden_states": false,
156
+ "output_scores": false,
157
+ "pad_token_id": null,
158
+ "patch_size": 16,
159
+ "prefix": null,
160
+ "problem_type": null,
161
+ "projection_dim": 512,
162
+ "pruned_heads": {},
163
+ "remove_invalid_values": false,
164
+ "repetition_penalty": 1.0,
165
+ "return_dict": true,
166
+ "return_dict_in_generate": false,
167
+ "sep_token_id": null,
168
+ "suppress_tokens": null,
169
+ "task_specific_params": null,
170
+ "temperature": 1.0,
171
+ "tf_legacy_loss": false,
172
+ "tie_encoder_decoder": false,
173
+ "tie_word_embeddings": true,
174
+ "tokenizer_class": null,
175
+ "top_k": 50,
176
+ "top_p": 1.0,
177
+ "torch_dtype": null,
178
+ "torchscript": false,
179
+ "transformers_version": "4.26.0",
180
+ "typical_p": 1.0,
181
+ "use_bfloat16": false
182
+ }
183
+ }
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": "VLEProcessor",
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 224
28
+ }
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "name_or_path": "vle-base",
9
+ "pad_token": "[PAD]",
10
+ "processor_class": "VLEProcessor",
11
+ "sep_token": "[SEP]",
12
+ "sp_model_kwargs": {},
13
+ "special_tokens_map_file": null,
14
+ "split_by_punct": false,
15
+ "tokenizer_class": "DebertaV2Tokenizer",
16
+ "unk_token": "[UNK]",
17
+ "vocab_type": "spm"
18
+ }