Is it possible to convert these to a single GGUF?
#2
by
smcleod
- opened
I've converted fp/bf16 safetensors models to GGUF in the past but not a 4bit model before - is this possible?
(For context this is so one could load the model with llama.cpp/Ollama).
These cannot be directly converted to GGUF but we are working on releasing a GGUF version of this model :)
smcleod
changed discussion status to
closed