Shideh Almasian commited on
Commit
0bb5b21
1 Parent(s): aca28ed
Files changed (2) hide show
  1. config.json +167 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/export/data/salmasia/numbert/fine_tune/roberta2roberta_fine_tuned_no_prefix_8epochs/roberta2roberta_fine_tune_no_prefixed_seed_4",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "roberta-base",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
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
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": 2,
22
+ "finetuning_task": null,
23
+ "forced_bos_token_id": null,
24
+ "forced_eos_token_id": null,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 514,
45
+ "min_length": 0,
46
+ "model_type": "roberta",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
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": "roberta-base",
84
+ "add_cross_attention": false,
85
+ "architectures": [
86
+ "RobertaForMaskedLM"
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_scores": false,
132
+ "pad_token_id": 1,
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
+ "torchscript": false,
150
+ "transformers_version": "4.7.0.dev0",
151
+ "type_vocab_size": 1,
152
+ "use_bfloat16": false,
153
+ "use_cache": true,
154
+ "vocab_size": 50265
155
+ },
156
+ "eos_token_id": 2,
157
+ "is_encoder_decoder": true,
158
+ "length_penalty": 2.0,
159
+ "max_length": 512,
160
+ "min_length": 56,
161
+ "model_type": "encoder-decoder",
162
+ "no_repeat_ngram_size": 2,
163
+ "num_beams": 4,
164
+ "pad_token_id": 1,
165
+ "transformers_version": null,
166
+ "vocab_size": 50265
167
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c82c6ef1225ecd1d5fc48ae9ce9647ec147d6abdc795dd44c33a9129b96519
3
+ size 1111071826