You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In our test, the performance of the gptq 4 bit model is better than that of the ggml 4bit, but the ggml inference speed is much faster.
So I'm thinking, can I convert the gptq model to ggml format? Can anyone give some suggestions?
The text was updated successfully, but these errors were encountered:
xinbingzhe
changed the title
A question about convert auto-gptq model to ggml format?
Question about convert auto-gptq model to ggml format?
Nov 6, 2023
In our test, the performance of the gptq 4 bit model is better than that of the ggml 4bit, but the ggml inference speed is much faster.
So I'm thinking, can I convert the gptq model to ggml format? Can anyone give some suggestions?
The text was updated successfully, but these errors were encountered: