GGUF quants
#1
by
lemon07r
- opened
Would love to see someone quant these to gguf. My llama.cpp setup on my Linux is broken atm so I can't convert it myself- @mradermacher (also if you could kindly do the gemma2-gutenberg-9b as well that would be amazing)
both are queued and should be available within a day. cheers :)
the gemma2 model lacks the (required) tokenizer.model file
both are queued and should be available within a day. cheers :)
Thanks a lot!
the gemma2 model lacks the (required) tokenizer.model file
Perhaps the one from the stock model would work? Not too sure if it works like that. Otherwise hopefully @nbeerbower can provide it.
Updated the gemma2 model. Thanks!
Psst, @mradermacher add it to the queue! haha
re-added. didn't expect such a quick fix :)