Hugging Face's logo

NPap
/
llama-2-7b-finetune

PEFT
PyTorch
llama
Model card Files Community
NPap commited on
Commit
1bf63b0
•
1 Parent(s): 4925bc1

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +4 -1
  2. special_tokens_map.json +3 -21
  3. tokenizer_config.json +41 -24
added_tokens.json CHANGED
@@ -1,3 +1,6 @@
1
  {
2
- "<pad>": 32000
 
 
 
3
  }
 
1
  {
2
+ "</s>": 2,
3
+ "<pad>": 32000,
4
+ "<s>": 1,
5
+ "<unk>": 0
6
  }
special_tokens_map.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
  "pad_token": "▁***",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "▁***",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
6
  }
tokenizer_config.json CHANGED
@@ -1,34 +1,51 @@
1
  {
2
  "add_bos_token": false,
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
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
- "pad_token": null,
24
  "sp_model_kwargs": {},
 
25
  "tokenizer_class": "LlamaTokenizer",
26
- "unk_token": {
27
- "__type": "AddedToken",
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false
33
- }
34
  }
 
1
  {
2
  "add_bos_token": false,
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": true,
32
+ "normalized": true,
33
+ "rstrip": true,
34
+ "single_word": false,
35
+ "special": false
36
+ }
37
  },
38
+ "additional_special_tokens": [],
39
+ "bos_token": "<s>",
40
  "clean_up_tokenization_spaces": false,
41
+ "eos_token": "</s>",
 
 
 
 
 
 
 
42
  "legacy": false,
43
  "model_max_length": 1000000000000000019884624838656,
44
+ "pad_token": "▁***",
45
  "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
  "tokenizer_class": "LlamaTokenizer",
48
+ "tokenizer_file": "/root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-chat-hf/snapshots/37892f30c23786c0d5367d80481fa0d9fba93cf8/tokenizer.json",
49
+ "unk_token": "<unk>",
50
+ "use_default_system_prompt": true
 
 
 
 
 
51
  }