Hugging Face's logo

phoner45
/
wangchan-sentiment-thai-text-model

Text Classification
Transformers
TensorBoard
Safetensors
Thai
camembert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
phoner45 commited on
Commit
74d5653
•
1 Parent(s): d198616

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +40 -0
  2. model.safetensors +3 -0
  3. runs/Oct10_03-49-57_8e29a928132b/events.out.tfevents.1728532201.8e29a928132b.563.0 +3 -0
  4. sentencepiece.bpe.model +3 -0
  5. special_tokens_map.json +20 -0
  6. tokenizer_config.json +92 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
3
+ "architectures": [
4
+ "CamembertForSequenceClassification"
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": "pos",
16
+ "1": "neu",
17
+ "2": "neg"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "neg": 2,
23
+ "neu": 1,
24
+ "pos": 0
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "camembert",
29
+ "num_attention_head": 12,
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.44.2",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 25005
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666ad0caf01b4590d70a93a66132121a288e3151de59f9b4e884daee28226a41
3
+ size 421011004
runs/Oct10_03-49-57_8e29a928132b/events.out.tfevents.1728532201.8e29a928132b.563.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ac4d8c13f4776e700a3b15585e3d3c6d3265ff803feccca52669666ae8dfd1
3
+ size 5719
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_config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "4": {
36
+ "content": "<unk>NOTUSED",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "</s>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<_>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<s>NOTUSED",
78
+ "</s>NOTUSED",
79
+ "<_>"
80
+ ],
81
+ "bos_token": "<s>",
82
+ "clean_up_tokenization_spaces": true,
83
+ "cls_token": "<s>",
84
+ "eos_token": "</s>",
85
+ "mask_token": "<mask>",
86
+ "model_max_length": 1000000000000000019884624838656,
87
+ "pad_token": "<pad>",
88
+ "sep_token": "</s>",
89
+ "sp_model_kwargs": {},
90
+ "tokenizer_class": "CamembertTokenizer",
91
+ "unk_token": "<unk>"
92
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a0a9cfbe2fff6433e909dd7367f3e25b841d94e8a5b3fd677ef9b8730f9a9d
3
+ size 5240