Hugging Face's logo

Thichow
/
test

TensorBoard
Safetensors
camembert
Model card Files
xet
 Metrics Community
Thichow commited on
Commit
778841f
·
verified ·
1 Parent(s): f1a390e

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +129 -0
  2. model.safetensors +3 -0
  3. runs/Jan21_13-52-57_06d51e5b6419/events.out.tfevents.1737467578.06d51e5b6419.1602.1 +3 -0
  4. sentencepiece.bpe.model +3 -0
  5. special_tokens_map.json +56 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +85 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "-100": "O",
16
+ "0": "ADVI",
17
+ "1": "ADVN",
18
+ "2": "ADVP",
19
+ "3": "ADVS",
20
+ "4": "CFQC",
21
+ "5": "CLTV",
22
+ "6": "CMTR",
23
+ "7": "CMTR@PUNC",
24
+ "8": "CNIT",
25
+ "9": "CVBL",
26
+ "10": "DCNM",
27
+ "11": "DDAC",
28
+ "12": "DDAN",
29
+ "13": "DDAQ",
30
+ "14": "DDBQ",
31
+ "15": "DIAC",
32
+ "16": "DIAQ",
33
+ "17": "DIBQ",
34
+ "18": "DONM",
35
+ "19": "EAFF",
36
+ "20": "EITT",
37
+ "21": "FIXN",
38
+ "22": "FIXV",
39
+ "23": "JCMP",
40
+ "24": "JCRG",
41
+ "25": "JSBR",
42
+ "26": "NCMN",
43
+ "27": "NCNM",
44
+ "28": "NEG",
45
+ "29": "NLBL",
46
+ "30": "NONM",
47
+ "31": "NPRP",
48
+ "32": "NTTL",
49
+ "33": "PDMN",
50
+ "34": "PNTR",
51
+ "35": "PPRS",
52
+ "36": "PREL",
53
+ "37": "PUNC",
54
+ "38": "RPRE",
55
+ "39": "VACT",
56
+ "40": "VATT",
57
+ "41": "VSTA",
58
+ "42": "XVAE",
59
+ "43": "XVAM",
60
+ "44": "XVBB",
61
+ "45": "XVBM",
62
+ "46": "XVMM"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "label2id": {
67
+ "ADVI": 0,
68
+ "ADVN": 1,
69
+ "ADVP": 2,
70
+ "ADVS": 3,
71
+ "CFQC": 4,
72
+ "CLTV": 5,
73
+ "CMTR": 6,
74
+ "CMTR@PUNC": 7,
75
+ "CNIT": 8,
76
+ "CVBL": 9,
77
+ "DCNM": 10,
78
+ "DDAC": 11,
79
+ "DDAN": 12,
80
+ "DDAQ": 13,
81
+ "DDBQ": 14,
82
+ "DIAC": 15,
83
+ "DIAQ": 16,
84
+ "DIBQ": 17,
85
+ "DONM": 18,
86
+ "EAFF": 19,
87
+ "EITT": 20,
88
+ "FIXN": 21,
89
+ "FIXV": 22,
90
+ "JCMP": 23,
91
+ "JCRG": 24,
92
+ "JSBR": 25,
93
+ "NCMN": 26,
94
+ "NCNM": 27,
95
+ "NEG": 28,
96
+ "NLBL": 29,
97
+ "NONM": 30,
98
+ "NPRP": 31,
99
+ "NTTL": 32,
100
+ "O": -100,
101
+ "PDMN": 33,
102
+ "PNTR": 34,
103
+ "PPRS": 35,
104
+ "PREL": 36,
105
+ "PUNC": 37,
106
+ "RPRE": 38,
107
+ "VACT": 39,
108
+ "VATT": 40,
109
+ "VSTA": 41,
110
+ "XVAE": 42,
111
+ "XVAM": 43,
112
+ "XVBB": 44,
113
+ "XVBM": 45,
114
+ "XVMM": 46
115
+ },
116
+ "layer_norm_eps": 1e-12,
117
+ "max_position_embeddings": 512,
118
+ "model_type": "camembert",
119
+ "num_attention_head": 12,
120
+ "num_attention_heads": 12,
121
+ "num_hidden_layers": 12,
122
+ "pad_token_id": 1,
123
+ "position_embedding_type": "absolute",
124
+ "torch_dtype": "float32",
125
+ "transformers_version": "4.47.1",
126
+ "type_vocab_size": 1,
127
+ "use_cache": true,
128
+ "vocab_size": 25005
129
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bf22ed9b564aabfa555454d4e8fbc8431a71e30f41f94fd5945d32b8e9b5ef
3
+ size 418786848
runs/Jan21_13-52-57_06d51e5b6419/events.out.tfevents.1737467578.06d51e5b6419.1602.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de386bb4a952da59aba4668679977c500ba4ed7290fad943b6066de0e7da4a85
3
+ size 7461
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<_>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "cls_token": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "eos_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "mask_token": {
29
+ "content": "<mask>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "pad_token": {
36
+ "content": "<pad>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "sep_token": {
43
+ "content": "</s>",
44
+ "lstrip": false,
45
+ "normalized": false,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ },
49
+ "unk_token": {
50
+ "content": "<unk>",
51
+ "lstrip": false,
52
+ "normalized": false,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ }
56
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "extra_special_tokens": {},
78
+ "mask_token": "<mask>",
79
+ "model_max_length": 416,
80
+ "pad_token": "<pad>",
81
+ "sep_token": "</s>",
82
+ "sp_model_kwargs": {},
83
+ "tokenizer_class": "CamembertTokenizer",
84
+ "unk_token": "<unk>"
85
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99f826c606204cd70495facb1c9d458e68c784912593c2bae116d3e4dcd4965
3
+ size 5304