extended-mind-mpt-30b-chat / tokenizer_config.json
phoebeklett's picture
Add tokenizer files
46568df verified
raw
history blame
1.35 kB
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif not 'system' in messages[0]['role'] %}{% set loop_messages = messages %}{% set system_message = 'A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if system_message != false %}{{ '<|im_start|>system\n' + system_message.strip() + '\n'}}{% endif %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% else %}{{ '\n' + '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% endif %}{% if (add_generation_prompt == true and loop.last) %}{{ '\n' + '<|im_start|>' + 'assistant' + '\n' }}{% elif (message['role'] == 'assistant') %}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"max_length": null,
"model_max_length": 8192,
"pad_to_multiple_of": null,
"pad_token": "<|endoftext|>",
"pad_token_type_id": 0,
"padding_side": "right",
"tokenizer_class": "GPTNeoXTokenizer",
"unk_token": "<|endoftext|>"
}