diff --git a/tokenizer_config.json b/tokenizer_config.json index e0422ac..94796fa 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -5,5 +5,13 @@ "tokenization_arcade100k.Arcade100kTokenizer", null ] - } + }, + "added_tokens_decoder": {}, + "bos_token": "<|endoftext|>", + "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 %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|endoftext|>", + "errors": "replace", + "model_max_length": 4096, + "pad_token": "<|endoftext|>" } \ No newline at end of file