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
ab17071
·
verified ·
1 Parent(s): c9df02a

Training in progress, step 100

Browse files
Files changed (6) hide show
  1. config.json +2 -2
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -8
  5. training_args.bin +1 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "hun3359/klue-bert-base-sentiment",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
@@ -36,5 +36,5 @@
36
  "transformers_version": "4.32.0",
37
  "type_vocab_size": 2,
38
  "use_cache": true,
39
- "vocab_size": 32000
40
  }
 
1
  {
2
+ "_name_or_path": "snunlp/KR-Medium",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
36
  "transformers_version": "4.32.0",
37
  "type_vocab_size": 2,
38
  "use_cache": true,
39
+ "vocab_size": 20000
40
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de98d87b6bb30c4c4a616cb073dd3203131c629559642b6f8d79691f7ef800e2
3
- size 442553582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147be1813fcf80388954aa1277772d9687f89fee2a8950c71423895bb36cb9b6
3
+ size 405689582
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -4,19 +4,12 @@
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
- "max_length": 512,
8
- "model_max_length": 512,
9
  "never_split": null,
10
- "pad_to_multiple_of": null,
11
  "pad_token": "[PAD]",
12
- "pad_token_type_id": 0,
13
- "padding_side": "right",
14
  "sep_token": "[SEP]",
15
- "stride": 0,
16
  "strip_accents": null,
17
  "tokenize_chinese_chars": true,
18
  "tokenizer_class": "BertTokenizer",
19
- "truncation_side": "right",
20
- "truncation_strategy": "longest_first",
21
  "unk_token": "[UNK]"
22
  }
 
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
 
8
  "never_split": null,
 
9
  "pad_token": "[PAD]",
 
 
10
  "sep_token": "[SEP]",
 
11
  "strip_accents": null,
12
  "tokenize_chinese_chars": true,
13
  "tokenizer_class": "BertTokenizer",
 
 
14
  "unk_token": "[UNK]"
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c72d1d268711ab46e9c77b0a8fef943a1c2f8be28afe0397f15b1c846dd77e50
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f414f98d344638f29343602ac0389fd1dda4071b1b1e73196e2e433fde83c64
3
  size 4472
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff