{ "add_prefix_space": false, "added_tokens_decoder": { "151643": { "content": "<|endoftext|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151644": { "content": "<|im_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151645": { "content": "<|im_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [ "<|im_start|>", "<|im_end|>" ], "bos_token": null, "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 %}{% if message['role'] == 'function_metadata' %}<|im_start|>tools\nYou have access to the following functions. Use them only if required:\n\n{{ message['content'] }}\n\nTo call a function, respond with a JSON object in this format:\n{\n \"name\": \"function_name\",\n \"arguments\": {\n \"argument1\": \"value1\",\n \"argument2\": \"value2\"\n }\n}\nRespond with a JSON object only if you wish to make a function call. Any other response will be treated as a regular query.When making a function call, provide only the JSON object, nothing else. Make one function call at a time. After the function call, wait for the response.\nOnly make use of the functions if they assist in providing the user with an answer. Otherwise, answer without making a function call.{% elif message['role'] == 'function_response' %}<|im_start|>function_response\nHere is the response to the function call. If helpful, use it to respond to the user's question:{{ message['content'] }}{% else %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% endif %}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}", "clean_up_tokenization_spaces": false, "eos_token": "<|im_end|>", "errors": "replace", "model_max_length": 32768, "pad_token": "<|endoftext|>", "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null }