Namoray commited on
Commit
673126a
·
1 Parent(s): 369f3c6

Fixed tokenizeokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +2 -21
  2. tokenizer_config.json +3 -4
special_tokens_map.json CHANGED
@@ -1,23 +1,4 @@
1
  {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|end_of_text|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|end_of_text|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "bos_token": "<|begin_of_text|>",
3
+ "eos_token": "<|end_of_text|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  }
tokenizer_config.json CHANGED
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "128001": {
12
- "content": "<|end_of_text|>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -2050,7 +2050,7 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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' }}{% else %}{{ eos_token }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
@@ -2058,6 +2058,5 @@
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
2061
- "pad_token": "<|eot_id|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
- }
 
9
  "special": true
10
  },
11
  "128001": {
12
+ "content": "<|eot_id|>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
+ "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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
 
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }