HieuAnh commited on
Commit
d7f8850
1 Parent(s): 024f038

Upload 7 files

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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-base",
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": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 258,
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "tokenizer_class": "PhobertTokenizer",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.35.2",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 64001
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5cceab6462408a6afa72d60367b6fbe2342086f597e26f439529b79b5ff9f3
3
+ size 540029536
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": true,
48
+ "eos_token": "</s>",
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 256,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "PhobertTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff