Hugging Face's logo

Kdogs
/
dapt_bert

Fill-Mask
Transformers
PyTorch
Korean
bert
Model card Files
xet
Community
2
Kdogs commited on
Commit
bb262a8
·
1 Parent(s): ddd7bb6

klue/roberta-sports-noNSP

Browse files
Files changed (6) hide show
  1. config.json +11 -13
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +2 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +5 -3
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,31 +1,29 @@
1
  {
2
- "_name_or_path": "beomi/kcbert-base",
3
  "architectures": [
4
- "BertForPreTraining"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
8
- "directionality": "bidi",
 
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 300,
16
  "model_type": "bert",
17
  "num_attention_heads": 12,
18
  "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "pooler_fc_size": 768,
21
- "pooler_num_attention_heads": 12,
22
- "pooler_num_fc_layers": 3,
23
- "pooler_size_per_head": 128,
24
- "pooler_type": "first_token_transform",
25
  "position_embedding_type": "absolute",
 
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.24.0",
28
- "type_vocab_size": 2,
29
  "use_cache": true,
30
- "vocab_size": 30000
31
  }
 
1
  {
2
+ "_name_or_path": "klue/roberta-base",
3
  "architectures": [
4
+ "BertForMaskedLM"
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
  "initializer_range": 0.02,
15
  "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
  "model_type": "bert",
19
  "num_attention_heads": 12,
20
  "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
 
 
 
 
 
22
  "position_embedding_type": "absolute",
23
+ "tokenizer_class": "BertTokenizer",
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.24.0",
26
+ "type_vocab_size": 1,
27
  "use_cache": true,
28
+ "vocab_size": 32000
29
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dd5b195ea69df11a4cf42ce4a48c74c311593ab9c794d0794dd184e1a3d4461
3
- size 438239971
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f9b76b6636e9cda315948a2b09326d45814fd55c090a6a1af325eeb4ae24f2
3
+ size 442678315
special_tokens_map.json CHANGED
@@ -1,5 +1,7 @@
1
  {
 
2
  "cls_token": "[CLS]",
 
3
  "mask_token": "[MASK]",
4
  "pad_token": "[PAD]",
5
  "sep_token": "[SEP]",
 
1
  {
2
+ "bos_token": "[CLS]",
3
  "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
  "mask_token": "[MASK]",
6
  "pad_token": "[PAD]",
7
  "sep_token": "[SEP]",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,14 +1,16 @@
1
  {
 
2
  "cls_token": "[CLS]",
3
  "do_basic_tokenize": true,
4
  "do_lower_case": false,
 
5
  "mask_token": "[MASK]",
6
- "model_max_length": 300,
7
- "name_or_path": "beomi/kcbert-base",
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
- "special_tokens_map_file": null,
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
  "tokenizer_class": "BertTokenizer",
 
1
  {
2
+ "bos_token": "[CLS]",
3
  "cls_token": "[CLS]",
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
  "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "name_or_path": "klue/roberta-base",
10
  "never_split": null,
11
  "pad_token": "[PAD]",
12
  "sep_token": "[SEP]",
13
+ "special_tokens_map_file": "/home/sifter/.cache/huggingface/hub/models--klue--roberta-base/snapshots/67dd433d36ebc66a42c9aaa85abcf8d2620e41d9/special_tokens_map.json",
14
  "strip_accents": null,
15
  "tokenize_chinese_chars": true,
16
  "tokenizer_class": "BertTokenizer",
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff