Arconte-13B
GUFF quants from ThenMagician/Arconte-13B.
I uploaded all of the guffs some time ago but I let the repo on private, my bad.
Imatrix quants were done from the f16 guff with a small subset of RP data I have, around 17 chunks, it achieved a perplexity of approximately 3.4 if I remember correctly.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.