GGUF quants?
#1
by
eleius
- opened
It seems generating gguf's for this model is not possible as either the pretokenizer is incorrect or not yet supported by llama: https://huggingface.co/mradermacher/JSL-MedMX-7X-GGUF/discussions/1
Any idea?
I would also be interested in GGUF quants if possible