lmzheng commited on
Commit
142d4e1
1 Parent(s): 681474e

Fix tokenizer configs

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +21 -4
  2. tokenizer_config.json +4 -6
special_tokens_map.json CHANGED
@@ -1,6 +1,23 @@
1
  {
2
- "bos_token": "</s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "</s>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "add_eos_token": false,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
- "content": "",
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
@@ -12,21 +12,19 @@
12
  "clean_up_tokenization_spaces": false,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
- "content": "",
16
  "lstrip": false,
17
  "normalized": true,
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
- "model_max_length": 2048,
22
  "pad_token": null,
23
- "padding_side": "right",
24
  "sp_model_kwargs": {},
25
- "special_tokens_map_file": "/home/gcpuser/hf-output/llama-7b/special_tokens_map.json",
26
  "tokenizer_class": "LlamaTokenizer",
27
  "unk_token": {
28
  "__type": "AddedToken",
29
- "content": "",
30
  "lstrip": false,
31
  "normalized": true,
32
  "rstrip": false,
 
3
  "add_eos_token": false,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
+ "content": "<s>",
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
 
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": 1000000000000000019884624838656,
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,