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
请问下,现在3.1,我要从qwen2.5-base上全参训sft,用的config是base,这个对最终对训练有影响,stop token的判定也有问题。训练出来最终的配置里eos token有问题
The text was updated successfully, but these errors were encountered:
使用swift infer推理正常嘛
Sorry, something went wrong.
qwen2.5-base上全参训sft,默认也会使用qwen2.5的template。里面有设置stop_words,只是不对config.json进行修改
推理用vllm和sglang都试过,不加stop=["<|im_end|>", "<|endoftext|>"],无法正常停止,看日志已经预测出了停止token,但依旧在进行预测,但无法看到后续的token
这个问题在之前2.x版本没有遇到过,是正常用base 基于instruct的config进行训练的
No branches or pull requests
请问下,现在3.1,我要从qwen2.5-base上全参训sft,用的config是base,这个对最终对训练有影响,stop token的判定也有问题。训练出来最终的配置里eos token有问题
The text was updated successfully, but these errors were encountered: