https://huggingface.co/Darkknight535/Moonlight-L3-15B-v2-64k

#367
by Ttimofeyka - opened

A new model from the author whose models you have already quantized (OpenCrystal). It has a context size of 64k, but it is based on L3.

Queued! You can watch its progress at http://hf.tst.eu/status.html (today is on the busy side).

And yeah, I quantize a lot of models from Darkknight535... :)

Cheers!

mradermacher changed discussion status to closed

Sign up or log in to comment