Hugging Face's logo

Pavarissy
/
wangchanberta-ud-thai-pud-upos

Token Classification
Transformers
PyTorch
Thai
camembert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Pavarissy commited on
Commit
a272cb4
•
1 Parent(s): f35abe5

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +69 -0
  2. pytorch_model.bin +3 -0
  3. sentencepiece.bpe.model +3 -0
  4. special_tokens_map.json +20 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +84 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
3
+ "architectures": [
4
+ "CamembertForTokenClassification"
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": "NOUN",
16
+ "1": "PUNCT",
17
+ "2": "ADP",
18
+ "3": "NUM",
19
+ "4": "SYM",
20
+ "5": "SCONJ",
21
+ "6": "ADJ",
22
+ "7": "PART",
23
+ "8": "DET",
24
+ "9": "CCONJ",
25
+ "10": "PROPN",
26
+ "11": "PRON",
27
+ "12": "X",
28
+ "13": "_",
29
+ "14": "ADV",
30
+ "15": "INTJ",
31
+ "16": "VERB",
32
+ "17": "AUX"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "ADJ": 6,
38
+ "ADP": 2,
39
+ "ADV": 14,
40
+ "AUX": 17,
41
+ "CCONJ": 9,
42
+ "DET": 8,
43
+ "INTJ": 15,
44
+ "NOUN": 0,
45
+ "NUM": 3,
46
+ "PART": 7,
47
+ "PRON": 11,
48
+ "PROPN": 10,
49
+ "PUNCT": 1,
50
+ "SCONJ": 5,
51
+ "SYM": 4,
52
+ "VERB": 16,
53
+ "X": 12,
54
+ "_": 13
55
+ },
56
+ "layer_norm_eps": 1e-12,
57
+ "max_position_embeddings": 512,
58
+ "model_type": "camembert",
59
+ "num_attention_head": 12,
60
+ "num_attention_heads": 12,
61
+ "num_hidden_layers": 12,
62
+ "pad_token_id": 1,
63
+ "position_embedding_type": "absolute",
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.34.1",
66
+ "type_vocab_size": 1,
67
+ "use_cache": true,
68
+ "vocab_size": 25005
69
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836e9ff2f2622ce9a32a929755949284fe7c6029b6eac7bb2d8fa912cf9a356f
3
+ size 418739430
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
3
+ size 904693
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<_>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
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>NOTUSED",
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
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "8": {
52
+ "content": "<_>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "25004": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<_>"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": true,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "mask_token": "<mask>",
78
+ "model_max_length": 1000000000000000019884624838656,
79
+ "pad_token": "<pad>",
80
+ "sep_token": "</s>",
81
+ "sp_model_kwargs": {},
82
+ "tokenizer_class": "CamembertTokenizer",
83
+ "unk_token": "<unk>"
84
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9853ef2e5c07e85fa66506acb74d3344bc324338736f6be5983cef1854d3dc4
3
+ size 4600