shenzhi-wang hiyouga commited on
Commit
576a724
1 Parent(s): 5b0d845

Update tokenizer_config.json (#2)

Browse files

- Update tokenizer_config.json (3de4931cf57a94e10ab8d1a6166655e932cf7f9f)


Co-authored-by: Yaowei Zheng <hiyouga@users.noreply.huggingface.co>

Files changed (1) hide show
  1. tokenizer_config.json +3 -5
tokenizer_config.json CHANGED
@@ -2050,16 +2050,14 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\\n\\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
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
- "pad_token": "<|eot_id|>",
2062
- "padding_side": "right",
2063
- "split_special_tokens": false,
2064
  "tokenizer_class": "PreTrainedTokenizerFast"
2065
- }
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{ '<|begin_of_text|>' }}{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% set loop_messages = messages[1:] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message | trim + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}{% 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
+ "pad_token": "<|eot_id|>",
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"
2060
  ],
2061
  "model_max_length": 1000000000000000019884624838656,
 
 
 
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }