DrNicefellow commited on
Commit
a40d483
1 Parent(s): c9fcbe8

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +13 -0
tokenizer_config.json CHANGED
@@ -2050,6 +2050,19 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
2053
  "clean_up_tokenization_spaces": true,
2054
  "eos_token": "<|end_of_text|>",
2055
  "model_input_names": [
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": false,
2055
+ "eos_token": "<|endoftext|>",
2056
+ "errors": "replace",
2057
+ "model_max_length": 131072,
2058
+ "pad_token": "<|PAD_TOKEN|>",
2059
+ "padding_side": "left",
2060
+ "split_special_tokens": false,
2061
+ "tokenizer_class": "Qwen2Tokenizer",
2062
+ "unk_token": null
2063
+ }
2064
+
2065
+
2066
  "clean_up_tokenization_spaces": true,
2067
  "eos_token": "<|end_of_text|>",
2068
  "model_input_names": [