lewtun HF staff commited on
Commit
c985a04
1 Parent(s): 6702b6f

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +2 -0
tokenizer_config.json CHANGED
@@ -31,6 +31,7 @@
31
  "</s>"
32
  ],
33
  "bos_token": "<s>",
 
34
  "clean_up_tokenization_spaces": false,
35
  "eos_token": "</s>",
36
  "legacy": true,
@@ -39,6 +40,7 @@
39
  "sp_model_kwargs": {},
40
  "spaces_between_special_tokens": false,
41
  "tokenizer_class": "LlamaTokenizer",
 
42
  "unk_token": "<unk>",
43
  "use_default_system_prompt": true
44
  }
 
31
  "</s>"
32
  ],
33
  "bos_token": "<s>",
34
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
35
  "clean_up_tokenization_spaces": false,
36
  "eos_token": "</s>",
37
  "legacy": true,
 
40
  "sp_model_kwargs": {},
41
  "spaces_between_special_tokens": false,
42
  "tokenizer_class": "LlamaTokenizer",
43
+ "truncation_side": "left",
44
  "unk_token": "<unk>",
45
  "use_default_system_prompt": true
46
  }