AlexWortega commited on
Commit
f0dfb63
·
verified ·
1 Parent(s): a733e60

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +15 -3
  2. tokenizer_config.json +1 -0
special_tokens_map.json CHANGED
@@ -6,12 +6,24 @@
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
- "eos_token": "</s>",
10
- "pad_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
11
  "unk_token": {
12
  "content": "<unk>",
13
  "lstrip": false,
14
- "normalized": true,
15
  "rstrip": false,
16
  "single_word": false
17
  }
 
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
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
26
+ "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  }
tokenizer_config.json CHANGED
@@ -125,6 +125,7 @@
125
  }
126
  },
127
  "bos_token": "<s>",
 
128
  "clean_up_tokenization_spaces": false,
129
  "eos_token": "</s>",
130
  "legacy": true,
 
125
  }
126
  },
127
  "bos_token": "<s>",
128
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
129
  "clean_up_tokenization_spaces": false,
130
  "eos_token": "</s>",
131
  "legacy": true,