manhtt-079 commited on
Commit
17d2017
1 Parent(s): b1c5a5f
README.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - vi
4
+ metrics:
5
+ - f1
6
+ pipeline_tag: token-classification
7
+ tags:
8
+ - transformer
9
+ - vietnamese
10
+ - nlp
11
+ - bert
12
+ - deberta
13
+ - deberta-v3
14
+ ---
15
+
16
+ # ViPubMedDeBERTa: A Vietnamese pretrained biomedical language representation model
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_head_size": 64,
3
+ "attention_probs_dropout_prob": 0.1,
4
+ "hidden_act": "gelu",
5
+ "hidden_dropout_prob": 0.1,
6
+ "hidden_size": 384,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 1536,
9
+ "layer_norm_eps": 1e-07,
10
+ "max_position_embeddings": 512,
11
+ "max_relative_positions": -1,
12
+ "model_type": "deberta-v2",
13
+ "norm_rel_ebd": "layer_norm",
14
+ "num_attention_heads": 6,
15
+ "num_hidden_layers": 12,
16
+ "pad_token_id": 0,
17
+ "pooler_dropout": 0,
18
+ "pooler_hidden_act": "gelu",
19
+ "pooler_hidden_size": 384,
20
+ "pos_att_type": "p2c|c2p",
21
+ "position_biased_input": false,
22
+ "position_buckets": 256,
23
+ "relative_attention": true,
24
+ "share_att_key": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.25.1",
27
+ "type_vocab_size": 0,
28
+ "vocab_size": 128000
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8902c6de52fdac3fed459829689f314f764a0e148ad81f097de97b26498bb8b
3
+ size 283755965
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba0ea97aa01613014a1950fb11713b90367a76c6a3fa8ca286b973f848552d5
3
+ size 480601272
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "name_or_path": "manhtt-079/vipubmed-deberta-xsmall",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "unk_token": "[UNK]",
16
+ "vocab_type": "spm"
17
+ }