Hugging Face's logo

GItaf
/
bert2bert-with-cross-attn-decoder

Text Generation
Transformers
PyTorch
bert
Model card Files
xet
 Community
1
GItaf commited on
Commit
5360a55
·
1 Parent(s): 6260a4b

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +22 -165
config.json CHANGED
@@ -1,170 +1,27 @@
1
  {
 
2
  "architectures": [
3
- "EncoderDecoderModel"
4
  ],
5
- "decoder": {
6
- "_name_or_path": "bert-base-uncased",
7
- "add_cross_attention": true,
8
- "architectures": [
9
- "BertForMaskedLM"
10
- ],
11
- "attention_probs_dropout_prob": 0.1,
12
- "bad_words_ids": null,
13
- "bos_token_id": null,
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": null,
23
- "exponential_decay_length_penalty": null,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "gradient_checkpointing": false,
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-12,
44
- "length_penalty": 1.0,
45
- "max_length": 20,
46
- "max_position_embeddings": 512,
47
- "min_length": 0,
48
- "model_type": "bert",
49
- "no_repeat_ngram_size": 0,
50
- "num_attention_heads": 12,
51
- "num_beam_groups": 1,
52
- "num_beams": 1,
53
- "num_hidden_layers": 12,
54
- "num_return_sequences": 1,
55
- "output_attentions": false,
56
- "output_hidden_states": false,
57
- "output_scores": false,
58
- "pad_token_id": 0,
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
- "tf_legacy_loss": false,
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": "4.21.2",
79
- "type_vocab_size": 2,
80
- "typical_p": 1.0,
81
- "use_bfloat16": false,
82
- "use_cache": true,
83
- "vocab_size": 30522
84
- },
85
- "encoder": {
86
- "_name_or_path": "bert-base-uncased",
87
- "add_cross_attention": false,
88
- "architectures": [
89
- "BertForMaskedLM"
90
- ],
91
- "attention_probs_dropout_prob": 0.1,
92
- "bad_words_ids": null,
93
- "bos_token_id": null,
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": null,
103
- "exponential_decay_length_penalty": null,
104
- "finetuning_task": null,
105
- "forced_bos_token_id": null,
106
- "forced_eos_token_id": null,
107
- "gradient_checkpointing": false,
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-12,
124
- "length_penalty": 1.0,
125
- "max_length": 20,
126
- "max_position_embeddings": 512,
127
- "min_length": 0,
128
- "model_type": "bert",
129
- "no_repeat_ngram_size": 0,
130
- "num_attention_heads": 12,
131
- "num_beam_groups": 1,
132
- "num_beams": 1,
133
- "num_hidden_layers": 12,
134
- "num_return_sequences": 1,
135
- "output_attentions": false,
136
- "output_hidden_states": false,
137
- "output_scores": false,
138
- "pad_token_id": 0,
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
- "tf_legacy_loss": false,
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": "4.21.2",
159
- "type_vocab_size": 2,
160
- "typical_p": 1.0,
161
- "use_bfloat16": false,
162
- "use_cache": true,
163
- "vocab_size": 30522
164
- },
165
- "is_encoder_decoder": true,
166
- "model_type": "encoder-decoder",
167
- "tie_encoder_decoder": true,
168
  "torch_dtype": "float32",
169
- "transformers_version": null
 
 
 
170
  }
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
+ "BertLMHeadModel"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "is_decoder": true,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.21.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
  }