mengzhouxia commited on
Commit
9d59239
1 Parent(s): cd30bc3

first commit

Browse files
Files changed (4) hide show
  1. config.json +93 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/n/fs/nlp-mengzhou/space2/out/RTE/CoFi-test-v3/RTE_sparsity0.6_reglr0.01_ce0.1_layerdistillv4/best",
3
+ "architectures": [
4
+ "CoFiBertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "do_layer_distill": true,
9
+ "finetuning_task": "rte",
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
+ "1": [
32
+ 3,
33
+ 6
34
+ ],
35
+ "2": [
36
+ 8,
37
+ 3,
38
+ 4,
39
+ 7
40
+ ],
41
+ "3": [
42
+ 1
43
+ ],
44
+ "4": [],
45
+ "5": [
46
+ 11
47
+ ],
48
+ "6": [
49
+ 1,
50
+ 2,
51
+ 3,
52
+ 10,
53
+ 11
54
+ ],
55
+ "7": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 6,
60
+ 7,
61
+ 11
62
+ ],
63
+ "8": [],
64
+ "9": [
65
+ 1,
66
+ 3,
67
+ 4,
68
+ 6,
69
+ 7,
70
+ 9,
71
+ 10
72
+ ],
73
+ "10": [
74
+ 1,
75
+ 4,
76
+ 5
77
+ ],
78
+ "11": [
79
+ 0,
80
+ 3,
81
+ 5,
82
+ 6,
83
+ 7,
84
+ 10,
85
+ 11
86
+ ]
87
+ },
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.17.0.dev0",
90
+ "type_vocab_size": 2,
91
+ "use_cache": true,
92
+ "vocab_size": 30522
93
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cabe50595ce7607974c715873766d5d5e7e087c4f0a2138fe27ccbb9efb3dd
3
+ size 235327785
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