Hugging Face's logo

joshanashakya
/
old_mini_codebert_sourcecode_nmt_pn2ja_200E_5e-05LR

Text2Text Generation
Transformers
PyTorch
encoder-decoder
Inference Endpoints
Model card Files Community
joshanashakya commited on
Commit
bf815e6
•
1 Parent(s): 9f4d29b

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +175 -0
config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./mini_model",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "microsoft/codebert-base",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaModel"
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
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 2,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "gelu",
29
+ "hidden_dropout_prob": 0.1,
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-05,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 514,
47
+ "min_length": 0,
48
+ "model_type": "roberta",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 12,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 3,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_past": true,
58
+ "output_scores": false,
59
+ "pad_token_id": 1,
60
+ "position_embedding_type": "absolute",
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.18.0",
79
+ "type_vocab_size": 1,
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": true,
83
+ "vocab_size": 50265
84
+ },
85
+ "decoder_start_token_id": 0,
86
+ "encoder": {
87
+ "_name_or_path": "microsoft/codebert-base",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "RobertaModel"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "bos_token_id": 0,
95
+ "chunk_size_feed_forward": 0,
96
+ "classifier_dropout": null,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "diversity_penalty": 0.0,
100
+ "do_sample": false,
101
+ "early_stopping": false,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "eos_token_id": 2,
104
+ "exponential_decay_length_penalty": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "gelu",
109
+ "hidden_dropout_prob": 0.1,
110
+ "hidden_size": 768,
111
+ "id2label": {
112
+ "0": "LABEL_0",
113
+ "1": "LABEL_1"
114
+ },
115
+ "initializer_range": 0.02,
116
+ "intermediate_size": 3072,
117
+ "is_decoder": false,
118
+ "is_encoder_decoder": false,
119
+ "label2id": {
120
+ "LABEL_0": 0,
121
+ "LABEL_1": 1
122
+ },
123
+ "layer_norm_eps": 1e-05,
124
+ "length_penalty": 1.0,
125
+ "max_length": 20,
126
+ "max_position_embeddings": 514,
127
+ "min_length": 0,
128
+ "model_type": "roberta",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 12,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_hidden_layers": 3,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_past": true,
138
+ "output_scores": false,
139
+ "pad_token_id": 1,
140
+ "position_embedding_type": "absolute",
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "pruned_heads": {},
144
+ "remove_invalid_values": false,
145
+ "repetition_penalty": 1.0,
146
+ "return_dict": true,
147
+ "return_dict_in_generate": false,
148
+ "sep_token_id": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tie_encoder_decoder": false,
152
+ "tie_word_embeddings": true,
153
+ "tokenizer_class": null,
154
+ "top_k": 50,
155
+ "top_p": 1.0,
156
+ "torch_dtype": null,
157
+ "torchscript": false,
158
+ "transformers_version": "4.18.0",
159
+ "type_vocab_size": 1,
160
+ "typical_p": 1.0,
161
+ "use_bfloat16": false,
162
+ "use_cache": true,
163
+ "vocab_size": 50265
164
+ },
165
+ "eos_token_id": 2,
166
+ "is_encoder_decoder": true,
167
+ "max_length": 450,
168
+ "model_type": "encoder-decoder",
169
+ "no_repeat_ngram_size": 3,
170
+ "pad_token_id": 1,
171
+ "tie_encoder_decoder": true,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": null,
174
+ "vocab_size": 50265
175
+ }