Add ExLlamaV2 quant link
#1
by
bartowski
- opened
If you'd like to include it that is
I would like to include it. I made a README change very close to when you made the PR, so there is a conflict. Can you pull the new changes to resolve the conflict?
bartowski
changed pull request status to
closed
@macadeliccc opened a new one, what went wrong with your GGUF out of curiousity?
I’m not sure if it’s supported. I tried 3 different quants and none of them would load on ooba or vanilla llama.cpp
Not sure 100% why but I pulled it for the time being until I know for sure. I’ve been reading into the gemma.cpp repo to get some more information