RonanMcGovern's picture
Upload tokenizer
1905a2c verified
{
"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
}