Hugging Face's logo

joshanashakya
/
old_codebert_sourcecode_nmt_ja2pn_50E_5e-05LR

Text2Text Generation
Transformers
PyTorch
encoder-decoder
Inference Endpoints
Model card Files Community
joshanashakya commited on
Commit
8954631
•
1 Parent(s): 6dbf8aa

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +174 -0
config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 2,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 514,
46
+ "min_length": 0,
47
+ "model_type": "roberta",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_past": true,
57
+ "output_scores": false,
58
+ "pad_token_id": 1,
59
+ "position_embedding_type": "absolute",
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "sep_token_id": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.18.0",
78
+ "type_vocab_size": 1,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 50265
83
+ },
84
+ "decoder_start_token_id": 0,
85
+ "encoder": {
86
+ "_name_or_path": "microsoft/codebert-base",
87
+ "add_cross_attention": false,
88
+ "architectures": [
89
+ "RobertaModel"
90
+ ],
91
+ "attention_probs_dropout_prob": 0.1,
92
+ "bad_words_ids": null,
93
+ "bos_token_id": 0,
94
+ "chunk_size_feed_forward": 0,
95
+ "classifier_dropout": null,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "early_stopping": false,
101
+ "encoder_no_repeat_ngram_size": 0,
102
+ "eos_token_id": 2,
103
+ "exponential_decay_length_penalty": null,
104
+ "finetuning_task": null,
105
+ "forced_bos_token_id": null,
106
+ "forced_eos_token_id": null,
107
+ "hidden_act": "gelu",
108
+ "hidden_dropout_prob": 0.1,
109
+ "hidden_size": 768,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 3072,
116
+ "is_decoder": false,
117
+ "is_encoder_decoder": false,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1
121
+ },
122
+ "layer_norm_eps": 1e-05,
123
+ "length_penalty": 1.0,
124
+ "max_length": 20,
125
+ "max_position_embeddings": 514,
126
+ "min_length": 0,
127
+ "model_type": "roberta",
128
+ "no_repeat_ngram_size": 0,
129
+ "num_attention_heads": 12,
130
+ "num_beam_groups": 1,
131
+ "num_beams": 1,
132
+ "num_hidden_layers": 12,
133
+ "num_return_sequences": 1,
134
+ "output_attentions": false,
135
+ "output_hidden_states": false,
136
+ "output_past": true,
137
+ "output_scores": false,
138
+ "pad_token_id": 1,
139
+ "position_embedding_type": "absolute",
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "pruned_heads": {},
143
+ "remove_invalid_values": false,
144
+ "repetition_penalty": 1.0,
145
+ "return_dict": true,
146
+ "return_dict_in_generate": false,
147
+ "sep_token_id": null,
148
+ "task_specific_params": null,
149
+ "temperature": 1.0,
150
+ "tie_encoder_decoder": false,
151
+ "tie_word_embeddings": true,
152
+ "tokenizer_class": null,
153
+ "top_k": 50,
154
+ "top_p": 1.0,
155
+ "torch_dtype": null,
156
+ "torchscript": false,
157
+ "transformers_version": "4.18.0",
158
+ "type_vocab_size": 1,
159
+ "typical_p": 1.0,
160
+ "use_bfloat16": false,
161
+ "use_cache": true,
162
+ "vocab_size": 50265
163
+ },
164
+ "eos_token_id": 2,
165
+ "is_encoder_decoder": true,
166
+ "max_length": 450,
167
+ "model_type": "encoder-decoder",
168
+ "no_repeat_ngram_size": 3,
169
+ "pad_token_id": 1,
170
+ "tie_encoder_decoder": true,
171
+ "torch_dtype": "float32",
172
+ "transformers_version": null,
173
+ "vocab_size": 50265
174
+ }