Hugging Face's logo

Peerawat2024
/
AmbatronBERTa

Safetensors
camembert
Model card Files Community
1
Peerawat2024 commited on
Commit
1ae2f29
•
1 Parent(s): 2153ef0

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +80 -0
  2. model.safetensors +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
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6",
22
+ "7": "LABEL_7",
23
+ "8": "LABEL_8",
24
+ "9": "LABEL_9",
25
+ "10": "LABEL_10",
26
+ "11": "LABEL_11",
27
+ "12": "LABEL_12",
28
+ "13": "LABEL_13",
29
+ "14": "LABEL_14",
30
+ "15": "LABEL_15",
31
+ "16": "LABEL_16",
32
+ "17": "LABEL_17",
33
+ "18": "LABEL_18",
34
+ "19": "LABEL_19",
35
+ "20": "LABEL_20",
36
+ "21": "LABEL_21",
37
+ "22": "LABEL_22"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_10": 10,
45
+ "LABEL_11": 11,
46
+ "LABEL_12": 12,
47
+ "LABEL_13": 13,
48
+ "LABEL_14": 14,
49
+ "LABEL_15": 15,
50
+ "LABEL_16": 16,
51
+ "LABEL_17": 17,
52
+ "LABEL_18": 18,
53
+ "LABEL_19": 19,
54
+ "LABEL_2": 2,
55
+ "LABEL_20": 20,
56
+ "LABEL_21": 21,
57
+ "LABEL_22": 22,
58
+ "LABEL_3": 3,
59
+ "LABEL_4": 4,
60
+ "LABEL_5": 5,
61
+ "LABEL_6": 6,
62
+ "LABEL_7": 7,
63
+ "LABEL_8": 8,
64
+ "LABEL_9": 9
65
+ },
66
+ "layer_norm_eps": 1e-12,
67
+ "max_position_embeddings": 512,
68
+ "model_type": "camembert",
69
+ "num_attention_head": 12,
70
+ "num_attention_heads": 12,
71
+ "num_hidden_layers": 12,
72
+ "pad_token_id": 1,
73
+ "position_embedding_type": "absolute",
74
+ "problem_type": "single_label_classification",
75
+ "torch_dtype": "float32",
76
+ "transformers_version": "4.44.2",
77
+ "type_vocab_size": 1,
78
+ "use_cache": true,
79
+ "vocab_size": 25005
80
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f43bba433f6d4b655be1b95c17070bb6920e02a808f450cea10bbc396e867f9
3
+ size 421072524
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": false
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
+ }