mengzhouxia commited on
Commit
72e0a5d
1 Parent(s): 89fd5b3

first commit

Browse files
Files changed (4) hide show
  1. config.json +104 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/n/fs/nlp-mengzhou/space2/out/CoLA/CoFi-test-v3/CoLA_sparsity0.6_reglr0.01_ce0.1_layerdistillv3",
3
+ "architectures": [
4
+ "CoFiBertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "do_layer_distill": true,
9
+ "finetuning_task": "cola",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "0": 0,
18
+ "1": 1
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "output_attentions": true,
26
+ "output_hidden_states": true,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "pruned_heads": {
30
+ "0": [
31
+ 0,
32
+ 4,
33
+ 5,
34
+ 7,
35
+ 11
36
+ ],
37
+ "1": [
38
+ 2,
39
+ 3,
40
+ 5,
41
+ 6,
42
+ 7,
43
+ 8
44
+ ],
45
+ "2": [
46
+ 2,
47
+ 3,
48
+ 4,
49
+ 5,
50
+ 7,
51
+ 8,
52
+ 11
53
+ ],
54
+ "3": [
55
+ 1,
56
+ 2,
57
+ 4,
58
+ 6,
59
+ 7
60
+ ],
61
+ "4": [
62
+ 1
63
+ ],
64
+ "5": [],
65
+ "6": [
66
+ 8,
67
+ 11,
68
+ 4,
69
+ 7
70
+ ],
71
+ "7": [
72
+ 0,
73
+ 3,
74
+ 6,
75
+ 7,
76
+ 8,
77
+ 11
78
+ ],
79
+ "8": [
80
+ 3
81
+ ],
82
+ "9": [
83
+ 0,
84
+ 3,
85
+ 4,
86
+ 6,
87
+ 7,
88
+ 9
89
+ ],
90
+ "10": [
91
+ 8,
92
+ 2,
93
+ 10
94
+ ],
95
+ "11": [
96
+ 8
97
+ ]
98
+ },
99
+ "torch_dtype": "float32",
100
+ "transformers_version": "4.17.0.dev0",
101
+ "type_vocab_size": 2,
102
+ "use_cache": true,
103
+ "vocab_size": 30522
104
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dafd06a98ccd37ff964de684da4c380d56de3534f2164f6e0d06b19456ce4085
3
+ size 234622321
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff