hus960
hus960
AI & ML interests
None yet
Organizations
None yet
hus960's activity
should check HF Write Token first, sometimes forget to input this filed .
2
#48 opened about 2 months ago
by
hus960
improve BPE pre-processing + LLaMA 3 and Deepseek support
1
#55 opened about 2 months ago
by
hus960
This doesn't work for Llama3 models
13
#44 opened 2 months ago
by
birgermoell
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1614079701740-6033e34a9aa44495c80dd043.jpeg)
Add IQ Quantization support with the help of imatrix and GPUs
7
#35 opened 3 months ago
by
qnixsynapse
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63119cc5af10c9efa1e9b620/HOUcXxq76kaBOA-SKtanE.jpeg)
Maybe impose a max model size?
3
#33 opened 3 months ago
by
pcuenq
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1617264212503-603d25b75f9d390ab190b777.jpeg)