{ "add_prefix_space": false, "additional_special_tokens": [ "<|reg_extra|>", "<|endoftext|>", "<|fim_prefix|>", "<|fim_middle|>", "<|fim_suffix|>", "<|fim_pad|>", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "<|endofprompt|>", "<|im_start|>", "<|im_end|>", "<|pause|>", "<|reg0|>", "<|reg1|>", "<|reg2|>", "<|reg3|>", "<|reg4|>", "<|reg5|>", "<|reg6|>", "<|reg7|>", "<|extra0|>" ], "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": "<|im_end|>", "tokenizer_class": "GPT2TokenizerFast", "model_max_length": 4096, "pad_token": "<|endoftext|>", "unk_token": "<|endoftext|>" }