Hugging Face's logo

GItaf
/
BERT-FINETUNE-MBTI-LM-BERT-FINETUNE-MBTI-LM-JointBERT-Warmup-from-LM

Text Generation
Transformers
PyTorch
bert
generated_from_trainer
Inference Endpoints
Model card Files Community
1
GItaf commited on
Commit
3c616ea
•
1 Parent(s): bfbbbfe

Model save

Browse files
Files changed (2) hide show
  1. config.json +22 -192
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,198 +1,28 @@
1
  {
 
2
  "architectures": [
3
- "MyEncoderDecoderModel"
4
  ],
5
- "decoder": {
6
- "_name_or_path": "GItaf/BERT-FINETUNE-MBTI-LM",
7
- "add_cross_attention": false,
8
- "architectures": [
9
- "BertLMHeadModel"
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": true,
72
- "tie_word_embeddings": true,
73
- "tokenizer_class": null,
74
- "top_k": 50,
75
- "top_p": 1.0,
76
- "torch_dtype": "float32",
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": "GItaf/BERT-FINETUNE-MBTI-LM",
87
- "add_cross_attention": false,
88
- "architectures": [
89
- "BertLMHeadModel"
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
- "2": "LABEL_2",
115
- "3": "LABEL_3",
116
- "4": "LABEL_4",
117
- "5": "LABEL_5",
118
- "6": "LABEL_6",
119
- "7": "LABEL_7",
120
- "8": "LABEL_8",
121
- "9": "LABEL_9",
122
- "10": "LABEL_10",
123
- "11": "LABEL_11",
124
- "12": "LABEL_12",
125
- "13": "LABEL_13",
126
- "14": "LABEL_14",
127
- "15": "LABEL_15"
128
- },
129
- "initializer_range": 0.02,
130
- "intermediate_size": 3072,
131
- "is_decoder": false,
132
- "is_encoder_decoder": false,
133
- "label2id": {
134
- "LABEL_0": 0,
135
- "LABEL_1": 1,
136
- "LABEL_10": 10,
137
- "LABEL_11": 11,
138
- "LABEL_12": 12,
139
- "LABEL_13": 13,
140
- "LABEL_14": 14,
141
- "LABEL_15": 15,
142
- "LABEL_2": 2,
143
- "LABEL_3": 3,
144
- "LABEL_4": 4,
145
- "LABEL_5": 5,
146
- "LABEL_6": 6,
147
- "LABEL_7": 7,
148
- "LABEL_8": 8,
149
- "LABEL_9": 9
150
- },
151
- "layer_norm_eps": 1e-12,
152
- "length_penalty": 1.0,
153
- "max_length": 20,
154
- "max_position_embeddings": 512,
155
- "min_length": 0,
156
- "model_type": "bert",
157
- "no_repeat_ngram_size": 0,
158
- "num_attention_heads": 12,
159
- "num_beam_groups": 1,
160
- "num_beams": 1,
161
- "num_hidden_layers": 12,
162
- "num_return_sequences": 1,
163
- "output_attentions": false,
164
- "output_hidden_states": false,
165
- "output_scores": false,
166
- "pad_token_id": 0,
167
- "position_embedding_type": "absolute",
168
- "prefix": null,
169
- "problem_type": null,
170
- "pruned_heads": {},
171
- "remove_invalid_values": false,
172
- "repetition_penalty": 1.0,
173
- "return_dict": true,
174
- "return_dict_in_generate": false,
175
- "sep_token_id": null,
176
- "task_specific_params": null,
177
- "temperature": 1.0,
178
- "tf_legacy_loss": false,
179
- "tie_encoder_decoder": true,
180
- "tie_word_embeddings": true,
181
- "tokenizer_class": null,
182
- "top_k": 50,
183
- "top_p": 1.0,
184
- "torch_dtype": "float32",
185
- "torchscript": false,
186
- "transformers_version": "4.21.2",
187
- "type_vocab_size": 2,
188
- "typical_p": 1.0,
189
- "use_bfloat16": false,
190
- "use_cache": true,
191
- "vocab_size": 30522
192
- },
193
- "is_encoder_decoder": true,
194
- "model_type": "encoder-decoder",
195
  "tie_encoder_decoder": true,
196
  "torch_dtype": "float32",
197
- "transformers_version": null
 
 
 
198
  }
 
1
  {
2
+ "_name_or_path": "GItaf/BERT-FINETUNE-MBTI-LM",
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
  "tie_encoder_decoder": true,
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.21.2",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 30522
28
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a4b3c1c398b30d6fe68ad495a74ab70847007e89a2f095f09f03f6d88b30d7f
3
- size 876182295
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fc344470a4c182a20e40aee3ca72380de1bf5545d6a6ff8cce7b01efb57487
3
+ size 438128811