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
375567e
·
verified ·
1 Parent(s): bfc8dc7

Training in progress, step 100

Browse files
Files changed (6) hide show
  1. config.json +16 -18
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +9 -2
  5. training_args.bin +1 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,29 +1,32 @@
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,
13
  "hidden_size": 768,
14
  "id2label": {
15
- "0": "item",
16
- "1": "non_item",
17
- "2": "garbage",
18
- "3": "review"
 
 
 
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
- "garbage": 2,
24
- "item": 0,
25
- "non_item": 1,
26
- "review": 3
 
 
 
27
  },
28
  "layer_norm_eps": 1e-12,
29
  "max_position_embeddings": 512,
@@ -31,16 +34,11 @@
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": "hun3359/klue-bert-base-sentiment",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
 
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
+ "0": "\uacf5\ud3ec",
13
+ "1": "\ub180\ub78c",
14
+ "2": "\ubd84\ub178",
15
+ "3": "\uc2ac\ud514",
16
+ "4": "\uc911\ub9bd",
17
+ "5": "\ud589\ubcf5",
18
+ "6": "\ud610\uc624"
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
+ "\uacf5\ud3ec": 0,
24
+ "\ub180\ub78c": 1,
25
+ "\ubd84\ub178": 2,
26
+ "\uc2ac\ud514": 3,
27
+ "\uc911\ub9bd": 4,
28
+ "\ud589\ubcf5": 5,
29
+ "\ud610\uc624": 6
30
  },
31
  "layer_norm_eps": 1e-12,
32
  "max_position_embeddings": 512,
 
34
  "num_attention_heads": 12,
35
  "num_hidden_layers": 12,
36
  "pad_token_id": 0,
 
 
 
 
 
37
  "position_embedding_type": "absolute",
38
  "problem_type": "single_label_classification",
39
  "torch_dtype": "float32",
40
  "transformers_version": "4.32.0",
41
  "type_vocab_size": 2,
42
  "use_cache": true,
43
+ "vocab_size": 32000
44
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c66af3a7cf8e580181c0e77c5e4f99d1647a355cff681a7e9653be26f15f7d7
3
- size 473270510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b258eb9e867ad2f0ea30dfbdf07043d94222704ed4baeff34e64620857ef564f
3
+ size 442559726
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2,14 +2,21 @@
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
  }
 
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34a11e7fc554f0646c33051c686f8e3536f96962865ff357826623c4b3b17111
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08d7a9e249c6bad0260fc3359986857449866f0156fd40edb782035deb414da
3
  size 4472
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff