fenffef commited on
Commit
4859e3d
1 Parent(s): 525dccf

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +99 -0
  2. pytorch_model.bin +3 -0
  3. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/media/HD0/CPT/models/bart-base-chinese",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 101,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 102,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 102,
27
+ "finetuning_task": "tnews",
28
+ "forced_eos_token_id": 102,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2",
34
+ "3": "LABEL_3",
35
+ "4": "LABEL_4",
36
+ "5": "LABEL_5",
37
+ "6": "LABEL_6",
38
+ "7": "LABEL_7",
39
+ "8": "LABEL_8",
40
+ "9": "LABEL_9",
41
+ "10": "LABEL_10",
42
+ "11": "LABEL_11",
43
+ "12": "LABEL_12",
44
+ "13": "LABEL_13",
45
+ "14": "LABEL_14"
46
+ },
47
+ "init_std": 0.02,
48
+ "is_encoder_decoder": true,
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_2": 2,
58
+ "LABEL_3": 3,
59
+ "LABEL_4": 4,
60
+ "LABEL_5": 5,
61
+ "LABEL_6": 6,
62
+ "LABEL_7": 7,
63
+ "LABEL_8": 8,
64
+ "LABEL_9": 9
65
+ },
66
+ "max_position_embeddings": 1024,
67
+ "model_type": "bart",
68
+ "no_repeat_ngram_size": 3,
69
+ "normalize_before": false,
70
+ "normalize_embedding": true,
71
+ "num_beams": 4,
72
+ "num_hidden_layers": 6,
73
+ "pad_token_id": 0,
74
+ "scale_embedding": false,
75
+ "task_specific_params": {
76
+ "summarization": {
77
+ "length_penalty": 1.0,
78
+ "max_length": 128,
79
+ "min_length": 12,
80
+ "num_beams": 4
81
+ },
82
+ "summarization_cnn": {
83
+ "length_penalty": 2.0,
84
+ "max_length": 142,
85
+ "min_length": 56,
86
+ "num_beams": 4
87
+ },
88
+ "summarization_xsum": {
89
+ "length_penalty": 1.0,
90
+ "max_length": 62,
91
+ "min_length": 11,
92
+ "num_beams": 6
93
+ }
94
+ },
95
+ "tokenizer_class": "BertTokenizer",
96
+ "transformers_version": "4.4.1",
97
+ "use_cache": true,
98
+ "vocab_size": 51271
99
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9026712aa4eed5a21874f34c4fea9f2bd38e5109d9ff36060dbbb1de36d50af
3
+ size 563278003
vocab.txt ADDED
The diff for this file is too large to render. See raw diff