Davidai commited on
Commit
424483b
1 Parent(s): e6b0f3e

Upload with huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "prajjwal1/bert-tiny",
7
+ "add_cross_attention": true,
8
+ "architectures": null,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bad_words_ids": null,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "classifier_dropout": null,
14
+ "cross_attention_hidden_size": null,
15
+ "decoder_start_token_id": null,
16
+ "diversity_penalty": 0.0,
17
+ "do_sample": false,
18
+ "early_stopping": false,
19
+ "encoder_no_repeat_ngram_size": 0,
20
+ "eos_token_id": null,
21
+ "exponential_decay_length_penalty": null,
22
+ "finetuning_task": null,
23
+ "forced_bos_token_id": null,
24
+ "forced_eos_token_id": null,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 128,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 512,
34
+ "is_decoder": true,
35
+ "is_encoder_decoder": false,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1
39
+ },
40
+ "layer_norm_eps": 1e-12,
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "max_position_embeddings": 512,
44
+ "min_length": 0,
45
+ "model_type": "bert",
46
+ "no_repeat_ngram_size": 0,
47
+ "num_attention_heads": 2,
48
+ "num_beam_groups": 1,
49
+ "num_beams": 1,
50
+ "num_hidden_layers": 2,
51
+ "num_return_sequences": 1,
52
+ "output_attentions": false,
53
+ "output_hidden_states": false,
54
+ "output_scores": false,
55
+ "pad_token_id": 0,
56
+ "position_embedding_type": "absolute",
57
+ "prefix": null,
58
+ "problem_type": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "sep_token_id": null,
65
+ "task_specific_params": null,
66
+ "temperature": 1.0,
67
+ "tie_encoder_decoder": false,
68
+ "tie_word_embeddings": true,
69
+ "tokenizer_class": null,
70
+ "top_k": 50,
71
+ "top_p": 1.0,
72
+ "torch_dtype": null,
73
+ "torchscript": false,
74
+ "transformers_version": "4.20.1",
75
+ "type_vocab_size": 2,
76
+ "typical_p": 1.0,
77
+ "use_bfloat16": false,
78
+ "use_cache": true,
79
+ "vocab_size": 30522
80
+ },
81
+ "decoder_start_token_id": 101,
82
+ "encoder": {
83
+ "_name_or_path": "prajjwal1/bert-tiny",
84
+ "add_cross_attention": false,
85
+ "architectures": null,
86
+ "attention_probs_dropout_prob": 0.1,
87
+ "bad_words_ids": null,
88
+ "bos_token_id": null,
89
+ "chunk_size_feed_forward": 0,
90
+ "classifier_dropout": null,
91
+ "cross_attention_hidden_size": null,
92
+ "decoder_start_token_id": null,
93
+ "diversity_penalty": 0.0,
94
+ "do_sample": false,
95
+ "early_stopping": false,
96
+ "encoder_no_repeat_ngram_size": 0,
97
+ "eos_token_id": null,
98
+ "exponential_decay_length_penalty": null,
99
+ "finetuning_task": null,
100
+ "forced_bos_token_id": null,
101
+ "forced_eos_token_id": null,
102
+ "hidden_act": "gelu",
103
+ "hidden_dropout_prob": 0.1,
104
+ "hidden_size": 128,
105
+ "id2label": {
106
+ "0": "LABEL_0",
107
+ "1": "LABEL_1"
108
+ },
109
+ "initializer_range": 0.02,
110
+ "intermediate_size": 512,
111
+ "is_decoder": false,
112
+ "is_encoder_decoder": false,
113
+ "label2id": {
114
+ "LABEL_0": 0,
115
+ "LABEL_1": 1
116
+ },
117
+ "layer_norm_eps": 1e-12,
118
+ "length_penalty": 1.0,
119
+ "max_length": 20,
120
+ "max_position_embeddings": 512,
121
+ "min_length": 0,
122
+ "model_type": "bert",
123
+ "no_repeat_ngram_size": 0,
124
+ "num_attention_heads": 2,
125
+ "num_beam_groups": 1,
126
+ "num_beams": 1,
127
+ "num_hidden_layers": 2,
128
+ "num_return_sequences": 1,
129
+ "output_attentions": false,
130
+ "output_hidden_states": false,
131
+ "output_scores": false,
132
+ "pad_token_id": 0,
133
+ "position_embedding_type": "absolute",
134
+ "prefix": null,
135
+ "problem_type": null,
136
+ "pruned_heads": {},
137
+ "remove_invalid_values": false,
138
+ "repetition_penalty": 1.0,
139
+ "return_dict": true,
140
+ "return_dict_in_generate": false,
141
+ "sep_token_id": null,
142
+ "task_specific_params": null,
143
+ "temperature": 1.0,
144
+ "tie_encoder_decoder": false,
145
+ "tie_word_embeddings": true,
146
+ "tokenizer_class": null,
147
+ "top_k": 50,
148
+ "top_p": 1.0,
149
+ "torch_dtype": null,
150
+ "torchscript": false,
151
+ "transformers_version": "4.20.1",
152
+ "type_vocab_size": 2,
153
+ "typical_p": 1.0,
154
+ "use_bfloat16": false,
155
+ "use_cache": true,
156
+ "vocab_size": 30522
157
+ },
158
+ "is_encoder_decoder": true,
159
+ "model_type": "encoder-decoder",
160
+ "pad_token_id": 0,
161
+ "torch_dtype": "float32",
162
+ "transformers_version": null,
163
+ "vocab_size": 30522
164
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41eab1e2869abb12698ed80ae366163190b7496900c67b23ca7e5ef18a63fc94
3
+ size 35783283
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "prajjwal1/bert-tiny",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff