12 lines
739 B
JSON
12 lines
739 B
JSON
|
{
|
||
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
||
|
|
"bos_token": "<|bos|>",
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"pad_token": "<|pad|>",
|
||
|
|
"unk_token": "<|unk|>",
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"model_max_length": 4096,
|
||
|
|
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|im_start|>system\n{{ message['content'] }}<|im_end|>\n{% elif message['role'] == 'user' %}<|im_start|>user\n{{ message['content'] }}<|im_end|>\n{% elif message['role'] == 'assistant' %}{% generation %}<|im_start|>assistant\n{{ message['content'] }}<|im_end|>\n{% endgeneration %}{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}\n"
|
||
|
|
}
|