JJTsao commited on
Commit
6f2564d
·
verified ·
1 Parent(s): 05a8e08

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +7 -7
  2. special_tokens_map.json +35 -5
  3. tokenizer_config.json +7 -0
config.json CHANGED
@@ -8,15 +8,15 @@
8
  "dropout": 0.1,
9
  "hidden_dim": 3072,
10
  "id2label": {
11
- "0": "LABEL_0",
12
- "1": "LABEL_1",
13
- "2": "LABEL_2"
14
  },
15
  "initializer_range": 0.02,
16
  "label2id": {
17
- "LABEL_0": 0,
18
- "LABEL_1": 1,
19
- "LABEL_2": 2
20
  },
21
  "max_position_embeddings": 512,
22
  "model_type": "distilbert",
@@ -29,6 +29,6 @@
29
  "sinusoidal_pos_embds": false,
30
  "tie_weights_": true,
31
  "torch_dtype": "float32",
32
- "transformers_version": "4.52.3",
33
  "vocab_size": 30522
34
  }
 
8
  "dropout": 0.1,
9
  "hidden_dim": 3072,
10
  "id2label": {
11
+ "0": "generic",
12
+ "1": "recommendation",
13
+ "2": "factual"
14
  },
15
  "initializer_range": 0.02,
16
  "label2id": {
17
+ "factual": 2,
18
+ "generic": 0,
19
+ "recommendation": 1
20
  },
21
  "max_position_embeddings": 512,
22
  "model_type": "distilbert",
 
29
  "sinusoidal_pos_embds": false,
30
  "tie_weights_": true,
31
  "torch_dtype": "float32",
32
+ "transformers_version": "4.51.3",
33
  "vocab_size": 30522
34
  }
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer_config.json CHANGED
@@ -46,11 +46,18 @@
46
  "do_lower_case": true,
47
  "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
 
49
  "model_max_length": 512,
 
50
  "pad_token": "[PAD]",
 
 
51
  "sep_token": "[SEP]",
 
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
  "tokenizer_class": "DistilBertTokenizer",
 
 
55
  "unk_token": "[UNK]"
56
  }
 
46
  "do_lower_case": true,
47
  "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
49
+ "max_length": 128,
50
  "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
  "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
  "sep_token": "[SEP]",
56
+ "stride": 0,
57
  "strip_accents": null,
58
  "tokenize_chinese_chars": true,
59
  "tokenizer_class": "DistilBertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
  "unk_token": "[UNK]"
63
  }