lekhnathrijal commited on
Commit
d0a3403
·
1 Parent(s): d157797

Upload MultiTaskClassifierPipeline

Browse files
Files changed (3) hide show
  1. config.json +19 -1
  2. special_tokens_map.json +35 -5
  3. tokenizer_config.json +3 -0
config.json CHANGED
@@ -1,10 +1,28 @@
1
  {
2
- "_name_or_path": "google-bert/bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
 
1
  {
2
+ "_name_or_path": "ai-research-lab/bert-question-classifier",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
+ "custom_pipelines": {
9
+ "question-classifier": {
10
+ "default": {
11
+ "model": {
12
+ "pt": [
13
+ "ai-research-lab/bert-question-classifier",
14
+ "main"
15
+ ]
16
+ }
17
+ },
18
+ "impl": "classifier_pipeline.MultiTaskClassifierPipeline",
19
+ "pt": [
20
+ "AutoModelForSequenceClassification"
21
+ ],
22
+ "tf": [],
23
+ "type": "text"
24
+ }
25
+ },
26
  "gradient_checkpointing": false,
27
  "hidden_act": "gelu",
28
  "hidden_dropout_prob": 0.1,
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
@@ -50,8 +50,11 @@
50
  "model_max_length": 512,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
 
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
 
50
  "model_max_length": 512,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
+ "stride": 0,
54
  "strip_accents": null,
55
  "tokenize_chinese_chars": true,
56
  "tokenizer_class": "BertTokenizer",
57
+ "truncation_side": "right",
58
+ "truncation_strategy": "longest_first",
59
  "unk_token": "[UNK]"
60
  }