🚩 No files available
#1
by
alvarobartt
HF staff
- opened
Hi here @mlabonne !
Nice and fast GGUF quantized weights of Google's Gemma models, just flagging that there are no files available here.
Ah maybe don't though, I'm just waiting for llama.cpp to fix the inference. :( I can upload the files but then people will flag it because it doesn't work haha
Oh fair! Indeed I'm using it now and seems to be working fine so far with llama-cpp-python, I'm filling a PR to add the gemma formatting
alvarobartt
changed discussion status to
closed
Pasting it here for reference in case that's useful to you @mlabonne https://github.com/abetlen/llama-cpp-python/pull/1210