Jan Philipp Harries commited on
Commit
b9396db
1 Parent(s): ada2077

fix tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +23 -30
tokenizer_config.json CHANGED
@@ -1,36 +1,23 @@
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": false
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": null,
@@ -38,7 +25,13 @@
38
  "sp_model_kwargs": {},
39
  "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": "/root/.cache/huggingface/hub/models--meta-llama--Llama-2-70b-hf/snapshots/cc8aa03a000ff08b4d5c5b39673321a2a396c396/tokenizer.json",
42
- "unk_token": "<unk>",
 
 
 
 
 
 
43
  "use_default_system_prompt": true
44
  }
 
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": false,
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": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
 
25
  "sp_model_kwargs": {},
26
  "spaces_between_special_tokens": false,
27
  "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
  "use_default_system_prompt": true
37
  }