CodeQwen1.5-7B / tokenizer_config.json
JustinLin610's picture
Upload folder using huggingface_hub
535391d verified
raw
history blame
974 Bytes
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": false,
"additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<fim_prefix>", "<fim_middle>", "<fim_suffix>", "<fim_pad>"],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<fim_pad>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"add_prefix_space": true,
"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 %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
}