We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
datasets/utils.py文件中,关于qwen2的bug,QWen2Tokenizer 应该改为 Qwen2Tokenizer
def get_bos_eos_token_ids(tokenizer): if tokenizer.__class__.__name__ in [ 'QWenTokenizer', 'QWen2Tokenizer', 'Qwen2TokenizerFast' ]: bos_token_id = [] eos_token_id = tokenizer.eos_token_id assert eos_token_id is not None, \ 'Please set eos_token for Qwen tokenizer!' elif tokenizer.__class__.__name__ == 'ChatGLMTokenizer': bos_token_id = [64790, 64792] eos_token_id = tokenizer.eos_token_id else: bos_token_id = tokenizer.bos_token_id eos_token_id = tokenizer.eos_token_id if isinstance(bos_token_id, int): bos_token_id = [bos_token_id] if isinstance(eos_token_id, int): eos_token_id = [eos_token_id] return bos_token_id, eos_token_id
The text was updated successfully, but these errors were encountered:
非常感谢你的反馈,确实有bug,你可以帮忙修复下吗?非常感谢
Sorry, something went wrong.
抱歉,公司电脑不太方便
No branches or pull requests
datasets/utils.py文件中,关于qwen2的bug,QWen2Tokenizer 应该改为 Qwen2Tokenizer
def get_bos_eos_token_ids(tokenizer): if tokenizer.__class__.__name__ in [ 'QWenTokenizer', 'QWen2Tokenizer', 'Qwen2TokenizerFast' ]: bos_token_id = [] eos_token_id = tokenizer.eos_token_id assert eos_token_id is not None, \ 'Please set eos_token for Qwen tokenizer!' elif tokenizer.__class__.__name__ == 'ChatGLMTokenizer': bos_token_id = [64790, 64792] eos_token_id = tokenizer.eos_token_id else: bos_token_id = tokenizer.bos_token_id eos_token_id = tokenizer.eos_token_id if isinstance(bos_token_id, int): bos_token_id = [bos_token_id] if isinstance(eos_token_id, int): eos_token_id = [eos_token_id] return bos_token_id, eos_token_id
The text was updated successfully, but these errors were encountered: