-
Notifications
You must be signed in to change notification settings - Fork 1.8k
New issue
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
请问运行Q4量化模型和ggml-FP16模型在效果上有何区别吗? #55
Comments
精度不一样,大多数情况下FP16的效果更好。 |
好的,thank u |
请问我运行了量化好的alpaca模型后,问他问题,比如:天空为什么是蓝色的?或者输入 你好,回答都是请你提供更多的细节,没有回复答案,请问这是什么情况呢 |
而且回复的还是英文 |
是不是这个问题? #11 |
我试了下的4bit量化模型,问天空为什么是蓝色的?回答还算正常。
|
模型并未针对多轮对话场景训练,所以在对话任务上的预期表现也不会十分理想。 |
我试了一下合并后的Pytorch版本模型,回答都正常,能正常回答谁是毛泽东,谁是刘德华。 |
那就是量化带来的影响比较大了,这一点我们从提供的模型上也无法避免。 |
No description provided.
The text was updated successfully, but these errors were encountered: