mrm8488 commited on
Commit
d74879d
1 Parent(s): c394ed9

Initial commit from mrm8488

Browse files
config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "microsoft/codebert-base",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "RobertaModel"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
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": 2,
21
+ "finetuning_task": null,
22
+ "forced_bos_token_id": null,
23
+ "forced_eos_token_id": null,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
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-05,
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "max_position_embeddings": 514,
44
+ "min_length": 0,
45
+ "model_type": "roberta",
46
+ "no_repeat_ngram_size": 0,
47
+ "num_attention_heads": 12,
48
+ "num_beam_groups": 1,
49
+ "num_beams": 1,
50
+ "num_hidden_layers": 12,
51
+ "num_return_sequences": 1,
52
+ "output_attentions": false,
53
+ "output_hidden_states": false,
54
+ "output_past": true,
55
+ "output_scores": false,
56
+ "pad_token_id": 1,
57
+ "position_embedding_type": "absolute",
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": "4.7.0.dev0",
75
+ "type_vocab_size": 1,
76
+ "use_bfloat16": false,
77
+ "use_cache": true,
78
+ "vocab_size": 50265
79
+ },
80
+ "decoder_start_token_id": 0,
81
+ "early_stopping": true,
82
+ "encoder": {
83
+ "_name_or_path": "microsoft/codebert-base",
84
+ "add_cross_attention": false,
85
+ "architectures": [
86
+ "RobertaModel"
87
+ ],
88
+ "attention_probs_dropout_prob": 0.1,
89
+ "bad_words_ids": null,
90
+ "bos_token_id": 0,
91
+ "chunk_size_feed_forward": 0,
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": 2,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "gradient_checkpointing": false,
102
+ "hidden_act": "gelu",
103
+ "hidden_dropout_prob": 0.1,
104
+ "hidden_size": 768,
105
+ "id2label": {
106
+ "0": "LABEL_0",
107
+ "1": "LABEL_1"
108
+ },
109
+ "initializer_range": 0.02,
110
+ "intermediate_size": 3072,
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-05,
118
+ "length_penalty": 1.0,
119
+ "max_length": 20,
120
+ "max_position_embeddings": 514,
121
+ "min_length": 0,
122
+ "model_type": "roberta",
123
+ "no_repeat_ngram_size": 0,
124
+ "num_attention_heads": 12,
125
+ "num_beam_groups": 1,
126
+ "num_beams": 1,
127
+ "num_hidden_layers": 12,
128
+ "num_return_sequences": 1,
129
+ "output_attentions": false,
130
+ "output_hidden_states": false,
131
+ "output_past": true,
132
+ "output_scores": false,
133
+ "pad_token_id": 1,
134
+ "position_embedding_type": "absolute",
135
+ "prefix": null,
136
+ "problem_type": null,
137
+ "pruned_heads": {},
138
+ "remove_invalid_values": false,
139
+ "repetition_penalty": 1.0,
140
+ "return_dict": true,
141
+ "return_dict_in_generate": false,
142
+ "sep_token_id": null,
143
+ "task_specific_params": null,
144
+ "temperature": 1.0,
145
+ "tie_encoder_decoder": false,
146
+ "tie_word_embeddings": true,
147
+ "tokenizer_class": null,
148
+ "top_k": 50,
149
+ "top_p": 1.0,
150
+ "torchscript": false,
151
+ "transformers_version": "4.7.0.dev0",
152
+ "type_vocab_size": 1,
153
+ "use_bfloat16": false,
154
+ "use_cache": true,
155
+ "vocab_size": 50265
156
+ },
157
+ "eos_token_id": 2,
158
+ "is_encoder_decoder": true,
159
+ "length_penalty": 2.0,
160
+ "max_length": 128,
161
+ "model_type": "encoder-decoder",
162
+ "no_repeat_ngram_size": 3,
163
+ "num_beams": 4,
164
+ "tie_encoder_decoder": true,
165
+ "transformers_version": null,
166
+ "vocab_size": 50265
167
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f430c4222d24c0243b9de97e1658e9bff3e1d8b795188daa70d9e875566e184e
3
+ size 614819429
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
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": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/4da22fec5578ecec5fbe32b80d5a43c6fb66b0f6ad5e359979463f0722ac3b5f.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "microsoft/codebert-base"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff