Hugging Face's logo

GItaf
/
JointGPT2-warmup-from-CLS

Text Generation
Transformers
PyTorch
gpt2
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Community
GItaf commited on
Commit
82400fb
•
1 Parent(s): 301c402

Model save

Browse files
Files changed (2) hide show
  1. config.json +69 -240
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,249 +1,78 @@
1
  {
 
 
2
  "architectures": [
3
- "MyEncoderDecoderModel"
4
  ],
5
- "decoder": {
6
- "_name_or_path": "GItaf/GPT2-CLS-Finetuned-MBTI",
7
- "activation_function": "gelu_new",
8
- "add_cross_attention": false,
9
- "architectures": [
10
- "GPT2ForSequenceClassification"
11
- ],
12
- "attn_pdrop": 0.1,
13
- "bad_words_ids": null,
14
- "bos_token_id": 50256,
15
- "chunk_size_feed_forward": 0,
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
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "exponential_decay_length_penalty": null,
25
- "finetuning_task": null,
26
- "forced_bos_token_id": null,
27
- "forced_eos_token_id": null,
28
- "id2label": {
29
- "0": "LABEL_0",
30
- "1": "LABEL_1",
31
- "2": "LABEL_2",
32
- "3": "LABEL_3",
33
- "4": "LABEL_4",
34
- "5": "LABEL_5",
35
- "6": "LABEL_6",
36
- "7": "LABEL_7",
37
- "8": "LABEL_8",
38
- "9": "LABEL_9",
39
- "10": "LABEL_10",
40
- "11": "LABEL_11",
41
- "12": "LABEL_12",
42
- "13": "LABEL_13",
43
- "14": "LABEL_14",
44
- "15": "LABEL_15"
45
- },
46
- "initializer_range": 0.02,
47
- "is_decoder": true,
48
- "is_encoder_decoder": false,
49
- "label2id": {
50
- "LABEL_0": 0,
51
- "LABEL_1": 1,
52
- "LABEL_10": 10,
53
- "LABEL_11": 11,
54
- "LABEL_12": 12,
55
- "LABEL_13": 13,
56
- "LABEL_14": 14,
57
- "LABEL_15": 15,
58
- "LABEL_2": 2,
59
- "LABEL_3": 3,
60
- "LABEL_4": 4,
61
- "LABEL_5": 5,
62
- "LABEL_6": 6,
63
- "LABEL_7": 7,
64
- "LABEL_8": 8,
65
- "LABEL_9": 9
66
- },
67
- "layer_norm_epsilon": 1e-05,
68
- "length_penalty": 1.0,
69
- "max_length": 20,
70
- "min_length": 0,
71
- "model_type": "gpt2",
72
- "n_ctx": 1024,
73
- "n_embd": 768,
74
- "n_head": 12,
75
- "n_inner": null,
76
- "n_layer": 12,
77
- "n_positions": 1024,
78
- "no_repeat_ngram_size": 0,
79
- "num_beam_groups": 1,
80
- "num_beams": 1,
81
- "num_return_sequences": 1,
82
- "output_attentions": false,
83
- "output_hidden_states": false,
84
- "output_scores": false,
85
- "pad_token_id": 50256,
86
- "prefix": null,
87
- "problem_type": null,
88
- "pruned_heads": {},
89
- "remove_invalid_values": false,
90
- "reorder_and_upcast_attn": false,
91
- "repetition_penalty": 1.0,
92
- "resid_pdrop": 0.1,
93
- "return_dict": true,
94
- "return_dict_in_generate": false,
95
- "scale_attn_by_inverse_layer_idx": false,
96
- "scale_attn_weights": true,
97
- "sep_token_id": null,
98
- "summary_activation": null,
99
- "summary_first_dropout": 0.1,
100
- "summary_proj_to_labels": true,
101
- "summary_type": "cls_index",
102
- "summary_use_proj": true,
103
- "task_specific_params": {
104
- "text-generation": {
105
- "do_sample": true,
106
- "max_length": 50
107
- }
108
- },
109
- "temperature": 1.0,
110
- "tf_legacy_loss": false,
111
- "tie_encoder_decoder": true,
112
- "tie_word_embeddings": true,
113
- "tokenizer_class": null,
114
- "top_k": 50,
115
- "top_p": 1.0,
116
- "torch_dtype": "float32",
117
- "torchscript": false,
118
- "transformers_version": "4.21.2",
119
- "typical_p": 1.0,
120
- "use_bfloat16": false,
121
- "use_cache": true,
122
- "vocab_size": 50257
123
  },
124
- "encoder": {
125
- "_name_or_path": "GItaf/GPT2-CLS-Finetuned-MBTI",
126
- "activation_function": "gelu_new",
127
- "add_cross_attention": false,
128
- "architectures": [
129
- "GPT2ForSequenceClassification"
130
- ],
131
- "attn_pdrop": 0.1,
132
- "bad_words_ids": null,
133
- "bos_token_id": 50256,
134
- "chunk_size_feed_forward": 0,
135
- "cross_attention_hidden_size": null,
136
- "decoder_start_token_id": null,
137
- "diversity_penalty": 0.0,
138
- "do_sample": false,
139
- "early_stopping": false,
140
- "embd_pdrop": 0.1,
141
- "encoder_no_repeat_ngram_size": 0,
142
- "eos_token_id": 50256,
143
- "exponential_decay_length_penalty": null,
144
- "finetuning_task": null,
145
- "forced_bos_token_id": null,
146
- "forced_eos_token_id": null,
147
- "id2label": {
148
- "0": "LABEL_0",
149
- "1": "LABEL_1",
150
- "2": "LABEL_2",
151
- "3": "LABEL_3",
152
- "4": "LABEL_4",
153
- "5": "LABEL_5",
154
- "6": "LABEL_6",
155
- "7": "LABEL_7",
156
- "8": "LABEL_8",
157
- "9": "LABEL_9",
158
- "10": "LABEL_10",
159
- "11": "LABEL_11",
160
- "12": "LABEL_12",
161
- "13": "LABEL_13",
162
- "14": "LABEL_14",
163
- "15": "LABEL_15"
164
- },
165
- "initializer_range": 0.02,
166
- "is_decoder": false,
167
- "is_encoder_decoder": false,
168
- "label2id": {
169
- "LABEL_0": 0,
170
- "LABEL_1": 1,
171
- "LABEL_10": 10,
172
- "LABEL_11": 11,
173
- "LABEL_12": 12,
174
- "LABEL_13": 13,
175
- "LABEL_14": 14,
176
- "LABEL_15": 15,
177
- "LABEL_2": 2,
178
- "LABEL_3": 3,
179
- "LABEL_4": 4,
180
- "LABEL_5": 5,
181
- "LABEL_6": 6,
182
- "LABEL_7": 7,
183
- "LABEL_8": 8,
184
- "LABEL_9": 9
185
- },
186
- "layer_norm_epsilon": 1e-05,
187
- "length_penalty": 1.0,
188
- "max_length": 20,
189
- "min_length": 0,
190
- "model_type": "gpt2",
191
- "n_ctx": 1024,
192
- "n_embd": 768,
193
- "n_head": 12,
194
- "n_inner": null,
195
- "n_layer": 12,
196
- "n_positions": 1024,
197
- "no_repeat_ngram_size": 0,
198
- "num_beam_groups": 1,
199
- "num_beams": 1,
200
- "num_return_sequences": 1,
201
- "output_attentions": false,
202
- "output_hidden_states": false,
203
- "output_scores": false,
204
- "pad_token_id": 50256,
205
- "prefix": null,
206
- "problem_type": null,
207
- "pruned_heads": {},
208
- "remove_invalid_values": false,
209
- "reorder_and_upcast_attn": false,
210
- "repetition_penalty": 1.0,
211
- "resid_pdrop": 0.1,
212
- "return_dict": true,
213
- "return_dict_in_generate": false,
214
- "scale_attn_by_inverse_layer_idx": false,
215
- "scale_attn_weights": true,
216
- "sep_token_id": null,
217
- "summary_activation": null,
218
- "summary_first_dropout": 0.1,
219
- "summary_proj_to_labels": true,
220
- "summary_type": "cls_index",
221
- "summary_use_proj": true,
222
- "task_specific_params": {
223
- "text-generation": {
224
- "do_sample": true,
225
- "max_length": 50
226
- }
227
- },
228
- "temperature": 1.0,
229
- "tf_legacy_loss": false,
230
- "tie_encoder_decoder": true,
231
- "tie_word_embeddings": true,
232
- "tokenizer_class": null,
233
- "top_k": 50,
234
- "top_p": 1.0,
235
- "torch_dtype": "float32",
236
- "torchscript": false,
237
- "transformers_version": "4.21.2",
238
- "typical_p": 1.0,
239
- "use_bfloat16": false,
240
- "use_cache": true,
241
- "vocab_size": 50257
242
  },
243
- "is_encoder_decoder": true,
244
- "model_type": "encoder-decoder",
 
 
 
 
 
 
245
  "pad_token_id": 50256,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
246
  "tie_encoder_decoder": true,
247
  "torch_dtype": "float32",
248
- "transformers_version": null
 
 
249
  }
 
1
  {
2
+ "_name_or_path": "GItaf/GPT2-CLS-Finetuned-MBTI",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
29
+ "initializer_range": 0.02,
30
+ "is_decoder": true,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_10": 10,
35
+ "LABEL_11": 11,
36
+ "LABEL_12": 12,
37
+ "LABEL_13": 13,
38
+ "LABEL_14": 14,
39
+ "LABEL_15": 15,
40
+ "LABEL_2": 2,
41
+ "LABEL_3": 3,
42
+ "LABEL_4": 4,
43
+ "LABEL_5": 5,
44
+ "LABEL_6": 6,
45
+ "LABEL_7": 7,
46
+ "LABEL_8": 8,
47
+ "LABEL_9": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  },
49
+ "layer_norm_epsilon": 1e-05,
50
+ "model_type": "gpt2",
51
+ "n_ctx": 1024,
52
+ "n_embd": 768,
53
+ "n_head": 12,
54
+ "n_inner": null,
55
+ "n_layer": 12,
56
+ "n_positions": 1024,
57
  "pad_token_id": 50256,
58
+ "reorder_and_upcast_attn": false,
59
+ "resid_pdrop": 0.1,
60
+ "scale_attn_by_inverse_layer_idx": false,
61
+ "scale_attn_weights": true,
62
+ "summary_activation": null,
63
+ "summary_first_dropout": 0.1,
64
+ "summary_proj_to_labels": true,
65
+ "summary_type": "cls_index",
66
+ "summary_use_proj": true,
67
+ "task_specific_params": {
68
+ "text-generation": {
69
+ "do_sample": true,
70
+ "max_length": 50
71
+ }
72
+ },
73
  "tie_encoder_decoder": true,
74
  "torch_dtype": "float32",
75
+ "transformers_version": "4.21.2",
76
+ "use_cache": true,
77
+ "vocab_size": 50257
78
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:941868dc665d9b792fa9cbc24da0328e162577341c744116d4e36a83702dda9b
3
- size 1020845967
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e7af8929521ef13a6694892c8b2d20fb37e8cfd617556f114ef763facc71ccc
3
+ size 510396521