codegood commited on
Commit
936329b
1 Parent(s): cf67c91

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +21 -3
  2. tokenizer_config.json +1 -0
special_tokens_map.json CHANGED
@@ -1,6 +1,24 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
  "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer_config.json CHANGED
@@ -316,6 +316,7 @@
316
  },
317
  "bos_token": "<|endoftext|>",
318
  "clean_up_tokenization_spaces": true,
 
319
  "eos_token": "<|endoftext|>",
320
  "model_max_length": 2048,
321
  "pad_token": "<|endoftext|>",
 
316
  },
317
  "bos_token": "<|endoftext|>",
318
  "clean_up_tokenization_spaces": true,
319
+ "device_map": "auto",
320
  "eos_token": "<|endoftext|>",
321
  "model_max_length": 2048,
322
  "pad_token": "<|endoftext|>",