70b - Llama-3 - Dolphin v2.9

#33
by SabinStargem - opened

Cognitive Computation released their finetune of Llama-3. I want to try out a imat of it and see if it is good. I am not sure whether they will do a standard GGUF of this model, like they had with 8b.

https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-70b

Sure! It's in the queue. static quants will be generated first, followed by imatrix ones. Can take a day or two.

mradermacher changed discussion status to closed

Sign up or log in to comment