Hugging Face's logo

orendar
/
en_he_roberta_shared

Text2Text Generation
Transformers
PyTorch
encoder-decoder
Inference Endpoints
Model card Files Community
orendar commited on
Commit
0f4fae0
•
1 Parent(s): 74c3ab1

add model

Browse files
Files changed (2) hide show
  1. config.json +178 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output/roberta_ed/checkpoint-566964",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "output/roberta-base",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.0,
13
+ "bad_words_ids": [
14
+ [
15
+ 3
16
+ ]
17
+ ],
18
+ "bos_token_id": 1,
19
+ "chunk_size_feed_forward": 0,
20
+ "classifier_dropout": 0.0,
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": 2,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": 0,
31
+ "forced_eos_token_id": 2,
32
+ "hidden_act": "gelu",
33
+ "hidden_dropout_prob": 0.1,
34
+ "hidden_size": 768,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": true,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 514,
51
+ "min_length": 0,
52
+ "model_type": "roberta",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 3,
63
+ "position_embedding_type": "absolute",
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": "float32",
80
+ "torchscript": false,
81
+ "transformers_version": "4.19.0.dev0",
82
+ "type_vocab_size": 1,
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "use_cache": true,
86
+ "vocab_size": 32000
87
+ },
88
+ "decoder_start_token_id": 2,
89
+ "encoder": {
90
+ "_name_or_path": "output/roberta-base",
91
+ "add_cross_attention": false,
92
+ "architectures": [
93
+ "RobertaForMaskedLM"
94
+ ],
95
+ "attention_probs_dropout_prob": 0.0,
96
+ "bad_words_ids": [
97
+ [
98
+ 3
99
+ ]
100
+ ],
101
+ "bos_token_id": 1,
102
+ "chunk_size_feed_forward": 0,
103
+ "classifier_dropout": 0.0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": 2,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "early_stopping": false,
109
+ "encoder_no_repeat_ngram_size": 0,
110
+ "eos_token_id": 2,
111
+ "exponential_decay_length_penalty": null,
112
+ "finetuning_task": null,
113
+ "forced_bos_token_id": 0,
114
+ "forced_eos_token_id": 2,
115
+ "hidden_act": "gelu",
116
+ "hidden_dropout_prob": 0.1,
117
+ "hidden_size": 768,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "initializer_range": 0.02,
123
+ "intermediate_size": 3072,
124
+ "is_decoder": false,
125
+ "is_encoder_decoder": false,
126
+ "label2id": {
127
+ "LABEL_0": 0,
128
+ "LABEL_1": 1
129
+ },
130
+ "layer_norm_eps": 1e-05,
131
+ "length_penalty": 1.0,
132
+ "max_length": 20,
133
+ "max_position_embeddings": 514,
134
+ "min_length": 0,
135
+ "model_type": "roberta",
136
+ "no_repeat_ngram_size": 0,
137
+ "num_attention_heads": 12,
138
+ "num_beam_groups": 1,
139
+ "num_beams": 1,
140
+ "num_hidden_layers": 12,
141
+ "num_return_sequences": 1,
142
+ "output_attentions": false,
143
+ "output_hidden_states": false,
144
+ "output_scores": false,
145
+ "pad_token_id": 3,
146
+ "position_embedding_type": "absolute",
147
+ "prefix": null,
148
+ "problem_type": null,
149
+ "pruned_heads": {},
150
+ "remove_invalid_values": false,
151
+ "repetition_penalty": 1.0,
152
+ "return_dict": true,
153
+ "return_dict_in_generate": false,
154
+ "sep_token_id": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": "float32",
163
+ "torchscript": false,
164
+ "transformers_version": "4.19.0.dev0",
165
+ "type_vocab_size": 1,
166
+ "typical_p": 1.0,
167
+ "use_bfloat16": false,
168
+ "use_cache": true,
169
+ "vocab_size": 32000
170
+ },
171
+ "is_encoder_decoder": true,
172
+ "model_type": "encoder-decoder",
173
+ "pad_token_id": 3,
174
+ "tie_encoder_decoder": true,
175
+ "torch_dtype": "float32",
176
+ "transformers_version": null,
177
+ "vocab_size": 32000
178
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52891214e0547c4c8b500c536eddd9a4a57daa9a49169383190b12318454fe2d
3
+ size 558590245