ArunaSaraswathy commited on
Commit
1da0357
1 Parent(s): bfa43ae

Upload 6 files

Browse files

model downloaded from cloud. preliminary test for con dataset

config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-PER",
14
+ "2": "I-PER",
15
+ "3": "B-ORG",
16
+ "4": "I-ORG",
17
+ "5": "B-LOC",
18
+ "6": "I-LOC",
19
+ "7": "B-MISC",
20
+ "8": "I-MISC"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "B-LOC": 5,
25
+ "B-MISC": 7,
26
+ "B-ORG": 3,
27
+ "B-PER": 1,
28
+ "I-LOC": 6,
29
+ "I-MISC": 8,
30
+ "I-ORG": 4,
31
+ "I-PER": 2,
32
+ "O": 0
33
+ },
34
+ "max_position_embeddings": 512,
35
+ "model_type": "distilbert",
36
+ "n_heads": 12,
37
+ "n_layers": 6,
38
+ "pad_token_id": 0,
39
+ "qa_dropout": 0.1,
40
+ "seq_classif_dropout": 0.2,
41
+ "sinusoidal_pos_embds": false,
42
+ "tie_weights_": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.17.0",
45
+ "vocab_size": 30522
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f6f0edc2ff46005744f51a2f204630faf2997e734098d45091b0c7e0834c8c7
3
+ size 265517557
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "./my_tbert_model/", "tokenizer_class": "DistilBertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff