Hugging Face's logo

promodoin9
/
code-search-net-tokenizer

Transformers
Inference Endpoints
Model card Files Community
promodoin9 commited on
Commit
0a32896
•
1 Parent(s): 8800e15

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +33 -3
  2. tokenizer.json +0 -0
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +37 -9
special_tokens_map.json CHANGED
@@ -1,5 +1,35 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,19 +1,47 @@
1
  {
2
- "add_prefix_space": false,
 
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
- "bos_token": "<|endoftext|>",
14
- "clean_up_tokenization_spaces": true,
15
- "eos_token": "<|endoftext|>",
16
- "model_max_length": 1024,
17
- "tokenizer_class": "GPT2Tokenizer",
18
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
19
  }
 
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
  },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": false,
39
+ "model_max_length": 2048,
40
+ "pad_token": "<unk>",
41
+ "padding_side": "right",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": false
47
  }