system
HF staff
commited on
Commit
4faca52
1 Parent(s): 52ae484

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +140 -0
config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "activation_function": "gelu_new",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "GPT2LMHeadModel"
10
+ ],
11
+ "attn_pdrop": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 50256,
14
+ "chunk_size_feed_forward": 0,
15
+ "decoder_start_token_id": null,
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "embd_pdrop": 0.1,
19
+ "eos_token_id": 50256,
20
+ "finetuning_task": null,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "is_decoder": true,
27
+ "is_encoder_decoder": false,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1
31
+ },
32
+ "layer_norm_epsilon": 1e-05,
33
+ "length_penalty": 1.0,
34
+ "max_length": 20,
35
+ "min_length": 0,
36
+ "model_type": "gpt2",
37
+ "n_ctx": 1024,
38
+ "n_embd": 768,
39
+ "n_head": 12,
40
+ "n_inner": null,
41
+ "n_layer": 12,
42
+ "n_positions": 1024,
43
+ "no_repeat_ngram_size": 0,
44
+ "num_beams": 1,
45
+ "num_return_sequences": 1,
46
+ "output_attentions": false,
47
+ "output_hidden_states": false,
48
+ "pad_token_id": null,
49
+ "prefix": null,
50
+ "pruned_heads": {},
51
+ "repetition_penalty": 1.0,
52
+ "resid_pdrop": 0.1,
53
+ "return_dict": false,
54
+ "summary_activation": null,
55
+ "summary_first_dropout": 0.1,
56
+ "summary_proj_to_labels": true,
57
+ "summary_type": "cls_index",
58
+ "summary_use_proj": true,
59
+ "task_specific_params": {
60
+ "text-generation": {
61
+ "do_sample": true,
62
+ "max_length": 50
63
+ }
64
+ },
65
+ "temperature": 1.0,
66
+ "top_k": 50,
67
+ "top_p": 1.0,
68
+ "torchscript": false,
69
+ "use_bfloat16": false,
70
+ "use_cache": true,
71
+ "vocab_size": 50257,
72
+ "xla_device": null
73
+ },
74
+ "decoder_start_token_id": 50256,
75
+ "encoder": {
76
+ "add_cross_attention": false,
77
+ "architectures": [
78
+ "BertForMaskedLM"
79
+ ],
80
+ "attention_probs_dropout_prob": 0.1,
81
+ "bad_words_ids": null,
82
+ "bos_token_id": null,
83
+ "chunk_size_feed_forward": 0,
84
+ "decoder_start_token_id": null,
85
+ "do_sample": false,
86
+ "early_stopping": false,
87
+ "eos_token_id": null,
88
+ "finetuning_task": null,
89
+ "gradient_checkpointing": false,
90
+ "hidden_act": "gelu",
91
+ "hidden_dropout_prob": 0.1,
92
+ "hidden_size": 768,
93
+ "id2label": {
94
+ "0": "LABEL_0",
95
+ "1": "LABEL_1"
96
+ },
97
+ "initializer_range": 0.02,
98
+ "intermediate_size": 3072,
99
+ "is_decoder": false,
100
+ "is_encoder_decoder": false,
101
+ "label2id": {
102
+ "LABEL_0": 0,
103
+ "LABEL_1": 1
104
+ },
105
+ "layer_norm_eps": 1e-12,
106
+ "length_penalty": 1.0,
107
+ "max_length": 20,
108
+ "max_position_embeddings": 512,
109
+ "min_length": 0,
110
+ "model_type": "bert",
111
+ "no_repeat_ngram_size": 0,
112
+ "num_attention_heads": 12,
113
+ "num_beams": 1,
114
+ "num_hidden_layers": 12,
115
+ "num_return_sequences": 1,
116
+ "output_attentions": false,
117
+ "output_hidden_states": false,
118
+ "pad_token_id": 0,
119
+ "prefix": null,
120
+ "pruned_heads": {},
121
+ "repetition_penalty": 1.0,
122
+ "return_dict": false,
123
+ "task_specific_params": null,
124
+ "temperature": 1.0,
125
+ "top_k": 50,
126
+ "top_p": 1.0,
127
+ "torchscript": false,
128
+ "type_vocab_size": 2,
129
+ "use_bfloat16": false,
130
+ "use_cache": true,
131
+ "vocab_size": 28996,
132
+ "xla_device": null
133
+ },
134
+ "eos_token_id": 50256,
135
+ "is_encoder_decoder": true,
136
+ "max_length": 142,
137
+ "min_length": 56,
138
+ "model_type": "encoder_decoder",
139
+ "no_repeat_ngram_size": 3
140
+ }