Hugging Face's logo

kaRThik757
/
krt_sample_llm_7b

PEFT
Safetensors
Model card Files Community
kaRThik757 commited on
Commit
8d7a933
·
1 Parent(s): ec29afe

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +1 -7
  2. tokenizer_config.json +24 -40
special_tokens_map.json CHANGED
@@ -13,13 +13,7 @@
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
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "[PAD]",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -1,49 +1,33 @@
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": true,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "32000": {
30
- "content": "[PAD]",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- }
37
  },
38
- "bos_token": "<s>",
39
  "clean_up_tokenization_spaces": false,
40
- "eos_token": "</s>",
41
- "legacy": true,
 
 
 
 
 
 
42
  "model_max_length": 2048,
43
- "pad_token": "[PAD]",
44
  "sp_model_kwargs": {},
45
- "spaces_between_special_tokens": false,
46
  "tokenizer_class": "LlamaTokenizer",
47
- "unk_token": "<unk>",
48
- "use_default_system_prompt": false
 
 
 
 
 
 
49
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "model_max_length": 2048,
22
+ "pad_token": null,
23
  "sp_model_kwargs": {},
 
24
  "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
  }