Token Classification
Transformers
Safetensors
Vietnamese
roberta
ner
biomedical
vietnamese
medical
cqhofsns commited on
Commit
71d7edf
·
verified ·
1 Parent(s): a2344ef

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +55 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +13 -0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "B-bien_phap_chan_doan",
16
+ "1": "B-bien_phap_dieu_tri",
17
+ "2": "B-nguyen_nhan_benh",
18
+ "3": "B-ten_benh",
19
+ "4": "B-trieu_chung_benh",
20
+ "5": "I-bien_phap_chan_doan",
21
+ "6": "I-bien_phap_dieu_tri",
22
+ "7": "I-nguyen_nhan_benh",
23
+ "8": "I-ten_benh",
24
+ "9": "I-trieu_chung_benh",
25
+ "10": "O"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "is_decoder": false,
30
+ "label2id": {
31
+ "B-bien_phap_chan_doan": 0,
32
+ "B-bien_phap_dieu_tri": 1,
33
+ "B-nguyen_nhan_benh": 2,
34
+ "B-ten_benh": 3,
35
+ "B-trieu_chung_benh": 4,
36
+ "I-bien_phap_chan_doan": 5,
37
+ "I-bien_phap_dieu_tri": 6,
38
+ "I-nguyen_nhan_benh": 7,
39
+ "I-ten_benh": 8,
40
+ "I-trieu_chung_benh": 9,
41
+ "O": 10
42
+ },
43
+ "layer_norm_eps": 1e-05,
44
+ "max_position_embeddings": 2050,
45
+ "model_type": "roberta",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 1,
49
+ "position_embedding_type": "absolute",
50
+ "tie_word_embeddings": true,
51
+ "transformers_version": "5.5.0",
52
+ "type_vocab_size": 1,
53
+ "use_cache": false,
54
+ "vocab_size": 20481
55
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54abff93ff348f85573c883528330a1d167dad6959a396d13209904a3c9793f7
3
+ size 409500004
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "is_local": false,
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "<pad>",
10
+ "sep_token": "</s>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "unk_token": "<unk>"
13
+ }