What about suzume?
#6 opened 12 days ago
by
BahamutRU
Here is a 4 bit GPTQ quantized version
#5 opened 25 days ago
by
chplushsieh
Can we use orthogonalization to make the LLaMa-3 (8B-70B) More Intelligent?
#4 opened 25 days ago
by
Joseph717171
exl2 quants
#3 opened about 1 month ago
by
Apel-sin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6306b84e5b87d4feaad50869/U4OTKpR8jtcFJV0ZCmPd8.jpeg)