archangel_sft-kto_llama30b ?
Hi mradermacher,
I wondering if you could GUFF this model? :
https://huggingface.co/ContextualAI/archangel_sft-kto_llama30b
I just tried one of their smaller models that has already been gguffed :
https://huggingface.co/asedmammad/Contextual_KTO_Mistral_PairRM-GGUF
and it's super smart for it's size! :)
Sure, I can always try. If nothing goes wrong, static and imatrix quants should be done in a day.
Thankyou :)
Feel free to mention the result of your testing - is it up to your expectations? :)
No unfortunately, this one is quite a disappointment. Very strange considering Contextual_KTO_Mistral_PairRM-GGUF was so stellar. Apologies for that, I really thought this one might shine. Thankyou again and apologies for the blunder.
Aww... we can't have nice things... And don't worry, it's not an issue to quantize a model that then turns out to be not perfect. In the end, all models disappoint a few months later anyway :)
Lol, True always something better around the corner. :)