Wants to know how to deploy model and try it for my own
#4
by
LeonBlue
- opened
No description provided.
Hi.
This should be moved to discussion, not Pull Request.
Can you move this to discussion and close this PR?
Also, there are many quantization methods(ex: GPTQ or GGML).
We cannot assure "Perfect Quality in generation" when using them, those are highly used in community.
Maybe you can try one.
Sincerely