Is it possible and meaningful to use llama.cpp for DeepSeek models to create a LoRA-adapter model? #12298
Unanswered
timo-kurtz
asked this question in
Q&A
Is it possible and meaningful to use llama.cpp for DeepSeek models to create a LoRA-adapter model?
#12298
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I want to ask if its is possible and meaningful to use llama.cpp for DeepSeek R1 models to create a LoRA-adapter model?
For example, there are also Qwen models used, which are not Llama models. Are they compatible?
Beta Was this translation helpful? Give feedback.
All reactions