mr4 commited on
Commit
af5fa91
1 Parent(s): 5267c3e

Add the first version

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sbt-bert-base-vi",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "Tiêu cực",
16
+ "1": "Tích cực",
17
+ "2": "Trung tính"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "Tiêu cực": 0,
23
+ "Tích cực": 2,
24
+ "Trung tính": 1
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 258,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "tokenizer_class": "PhobertTokenizer",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.26.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 64001
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b7334b665e30267c20af7594b7ec925da94f6a5d4748684da2ca5a0667bb5f
3
+ size 540070837
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "model_max_length": 256,
7
+ "name_or_path": "sbt-bert-base-vi",
8
+ "pad_token": "<pad>",
9
+ "sep_token": "</s>",
10
+ "special_tokens_map_file": null,
11
+ "tokenizer_class": "PhobertTokenizer",
12
+ "unk_token": "<unk>"
13
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff