mradermacher

/

falcon-180B-i1-GGUF

like 2

II'll have a look and put it in the queue

The main challenge is that it needs convert-hf, which loads the model into memory. This is going to be very slow, but I'll try my best.

cool hope you make xs and xss versions, too.

I just came across this mixtral merge here:

https://huggingface.co/ibivibiv/orthorus-125b-v2

The quants are now slowly coming in (as you have seen).

I'll queue up the orthorus v2, although I haven't had time to check out the 125b-moe one yet :)