Hugging Face's logo

dd3434
/
test_model

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
1
dd3434 commited on
Commit
d68bd1b
·
verified ·
1 Parent(s): a37c975

Training in progress, step 100

Browse files
Files changed (6) hide show
  1. config.json +5 -10
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +9 -1
  4. spiece.model +3 -0
  5. tokenizer_config.json +18 -8
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,12 +1,11 @@
1
  {
2
- "_name_or_path": "kykim/bert-kor-base",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
8
- "directionality": "bidi",
9
- "embedding_size": 768,
10
  "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
@@ -19,6 +18,7 @@
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
 
22
  "label2id": {
23
  "garbage": 2,
24
  "item": 0,
@@ -30,17 +30,12 @@
30
  "model_type": "bert",
31
  "num_attention_heads": 12,
32
  "num_hidden_layers": 12,
33
- "pad_token_id": 0,
34
- "pooler_fc_size": 768,
35
- "pooler_num_attention_heads": 12,
36
- "pooler_num_fc_layers": 3,
37
- "pooler_size_per_head": 128,
38
- "pooler_type": "first_token_transform",
39
  "position_embedding_type": "absolute",
40
  "problem_type": "single_label_classification",
41
  "torch_dtype": "float32",
42
  "transformers_version": "4.32.0",
43
  "type_vocab_size": 2,
44
  "use_cache": true,
45
- "vocab_size": 42000
46
  }
 
1
  {
2
+ "_name_or_path": "skt/kobert-base-v1",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "author": "Heewon Jeon(madjakarta@gmail.com)",
8
  "classifier_dropout": null,
 
 
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
 
18
  },
19
  "initializer_range": 0.02,
20
  "intermediate_size": 3072,
21
+ "kobert_version": 1.0,
22
  "label2id": {
23
  "garbage": 2,
24
  "item": 0,
 
30
  "model_type": "bert",
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
  "torch_dtype": "float32",
37
  "transformers_version": "4.32.0",
38
  "type_vocab_size": 2,
39
  "use_cache": true,
40
+ "vocab_size": 8002
41
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cccc4956807c02c30dc937e93cd5cd3619401419d2dd4d84bd63bed1d395175
3
- size 473270510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513fd482d0e4170d3db2b1b4d9f8434ae51659a35973fc03bf4af8b934830a3c
3
+ size 368828654
special_tokens_map.json CHANGED
@@ -1,6 +1,14 @@
1
  {
 
2
  "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
 
 
 
 
 
 
 
4
  "pad_token": "[PAD]",
5
  "sep_token": "[SEP]",
6
  "unk_token": "[UNK]"
 
1
  {
2
+ "bos_token": "[CLS]",
3
  "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
  "pad_token": "[PAD]",
13
  "sep_token": "[SEP]",
14
  "unk_token": "[UNK]"
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17dc471055592d3cc9e0a5831e769246a8a001a4d27551c9ed79668173c7b407
3
+ size 371427
tokenizer_config.json CHANGED
@@ -1,15 +1,25 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 512,
8
- "never_split": null,
 
 
 
 
 
 
 
 
9
  "pad_token": "[PAD]",
 
10
  "sep_token": "[SEP]",
11
- "strip_accents": false,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
  "unk_token": "[UNK]"
15
  }
 
1
  {
2
+ "additional_special_tokens": null,
3
+ "bos_token": "[CLS]",
4
  "clean_up_tokenization_spaces": true,
5
  "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "keep_accents": false,
9
+ "last_hidden_states": true,
10
+ "mask_token": {
11
+ "__type": "AddedToken",
12
+ "content": "[MASK]",
13
+ "lstrip": true,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "model_max_length": 1000000000000000019884624838656,
19
  "pad_token": "[PAD]",
20
+ "remove_space": true,
21
  "sep_token": "[SEP]",
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "KoBERTTokenizer",
 
24
  "unk_token": "[UNK]"
25
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76cd85874cd4ae2e0bbe02ee764f0654ece5becd8ce62bba6b8ccdaf891a42c5
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7692193ebd95d5f82c07ef79a36a1c829666d01b230ac1c3d73a689da649bae
3
  size 4472