raynardj commited on
Commit
5ee2133
1 Parent(s): 08f3b21
Files changed (2) hide show
  1. config.json +177 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "uer/gpt2-chinese-poem",
7
+ "activation_function": "gelu_new",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "embd_pdrop": 0.1,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 50256,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "is_decoder": true,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "layer_norm_epsilon": 1e-05,
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "min_length": 0,
42
+ "model_type": "gpt2",
43
+ "n_ctx": 1024,
44
+ "n_embd": 768,
45
+ "n_head": 12,
46
+ "n_inner": null,
47
+ "n_layer": 12,
48
+ "n_positions": 1024,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_past": true,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "resid_pdrop": 0.1,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "scale_attn_weights": true,
67
+ "sep_token_id": null,
68
+ "summary_activation": null,
69
+ "summary_first_dropout": 0.1,
70
+ "summary_proj_to_labels": true,
71
+ "summary_type": "cls_index",
72
+ "summary_use_proj": true,
73
+ "task_specific_params": {
74
+ "text-generation": {
75
+ "do_sample": true,
76
+ "max_length": 120
77
+ }
78
+ },
79
+ "temperature": 1.0,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": true,
82
+ "tokenizer_class": "BertTokenizer",
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": null,
86
+ "torchscript": false,
87
+ "transformers_version": "4.9.1",
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "vocab_size": 22557
91
+ },
92
+ "encoder": {
93
+ "_name_or_path": "bert-base-chinese",
94
+ "add_cross_attention": false,
95
+ "architectures": [
96
+ "BertForMaskedLM"
97
+ ],
98
+ "attention_probs_dropout_prob": 0.1,
99
+ "bad_words_ids": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "decoder_start_token_id": null,
103
+ "directionality": "bidi",
104
+ "diversity_penalty": 0.0,
105
+ "do_sample": false,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "gradient_checkpointing": false,
113
+ "hidden_act": "gelu",
114
+ "hidden_dropout_prob": 0.1,
115
+ "hidden_size": 768,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3072,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "layer_norm_eps": 1e-12,
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "max_position_embeddings": 512,
132
+ "min_length": 0,
133
+ "model_type": "bert",
134
+ "no_repeat_ngram_size": 0,
135
+ "num_attention_heads": 12,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_hidden_layers": 12,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": 0,
144
+ "pooler_fc_size": 768,
145
+ "pooler_num_attention_heads": 12,
146
+ "pooler_num_fc_layers": 3,
147
+ "pooler_size_per_head": 128,
148
+ "pooler_type": "first_token_transform",
149
+ "position_embedding_type": "absolute",
150
+ "prefix": null,
151
+ "problem_type": null,
152
+ "pruned_heads": {},
153
+ "remove_invalid_values": false,
154
+ "repetition_penalty": 1.0,
155
+ "return_dict": true,
156
+ "return_dict_in_generate": false,
157
+ "sep_token_id": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tie_encoder_decoder": false,
161
+ "tie_word_embeddings": true,
162
+ "tokenizer_class": null,
163
+ "top_k": 50,
164
+ "top_p": 1.0,
165
+ "torch_dtype": null,
166
+ "torchscript": false,
167
+ "transformers_version": "4.9.1",
168
+ "type_vocab_size": 2,
169
+ "use_bfloat16": false,
170
+ "use_cache": true,
171
+ "vocab_size": 21128
172
+ },
173
+ "is_encoder_decoder": true,
174
+ "model_type": "encoder-decoder",
175
+ "torch_dtype": "float32",
176
+ "transformers_version": null
177
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:101cefbeb0838cc6a6e4b37d535673143a5d9498c29b2a3fd9831859e802fc76
3
+ size 960569915