orvp commited on
Commit
6801619
·
verified ·
1 Parent(s): 390559f

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +2 -3
  2. tokenizer_config.json +2 -3
special_tokens_map.json CHANGED
@@ -7,11 +7,10 @@
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": "<|end_of_text|>"
17
  }
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|eot_id|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
+ }
 
16
  }
tokenizer_config.json CHANGED
@@ -2050,14 +2050,13 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content'] }}{% elif message['role'] == 'user' %}{{ '\n\nHuman: ' + message['content'] + eos_token }}{% elif message['role'] == 'assistant' %}{{ '\n\nAssistant: ' + message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\nAssistant: ' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|end_of_text|>",
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
2061
- "pad_token": "<|end_of_text|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }
 
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 %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
 
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
  }