Hugging Face's logo

npvinHnivqn
/
gte_test_model

Feature Extraction
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Inference Endpoints
Model card Files Metrics Community
npvinHnivqn commited on
Commit
6768a73
•
1 Parent(s): 015807a

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -13
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +23 -28
special_tokens_map.json CHANGED
@@ -1,34 +1,27 @@
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,
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "</s>",
 
 
 
 
 
 
 
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "unk_token": {
24
+ "content": "<unk>",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,62 +1,57 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
- "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
- "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
- "mask_token": "[MASK]",
48
- "max_length": 512,
49
- "model_max_length": 32768,
50
- "pad_to_multiple_of": null,
51
- "pad_token": "[PAD]",
52
- "pad_token_type_id": 0,
53
- "padding_side": "right",
54
- "sep_token": "[SEP]",
55
- "stride": 0,
56
- "strip_accents": null,
57
- "tokenize_chinese_chars": true,
58
- "tokenizer_class": "BertTokenizer",
59
- "truncation_side": "right",
60
- "truncation_strategy": "longest_first",
61
- "unk_token": "[UNK]"
62
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
+ "content": "<unk>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
+ "1": {
14
+ "content": "<s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
+ "2": {
22
+ "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "46303": {
30
+ "content": "<|im_end|>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "46304": {
38
+ "content": "<|im_start|>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
+ "special": false
44
  }
45
  },
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": false,
48
+ "eos_token": "<|im_end|>",
49
+ "legacy": false,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "LlamaTokenizer",
54
+ "unk_token": "<unk>",
55
+ "use_default_system_prompt": true,
56
+ "use_fast": true
 
 
 
 
 
 
 
57
  }