CUDA extension not installed (even after manual compile and pip install)
1
#26 opened 15 days ago
by
markemicek
GGUF format
#25 opened 8 months ago
by
giladgd
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/DLeSZZ6VdvwK0ueKuUBiW.png)
TypeError: 'NoneType' object is not iterable in .../models_settings.py
#24 opened 9 months ago
by
thinktink
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fudo3K87Gwf2pE5gHhdbA.png)
Calibration dataset used to perform GPTQ
#23 opened 10 months ago
by
ht-rohit
A weird bug
11
#22 opened 10 months ago
by
XceptDev
Offloading to cpu not working?
1
#21 opened 10 months ago
by
fahadh4ilyas
May I ask why the GPTQ version is slow
#20 opened 11 months ago
by
lynngao815
can you upload a falcon-40b-GPTQ?
2
#18 opened 12 months ago
by
Gian-hf
Update README.md
#17 opened 12 months ago
by
saattrupdan
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1624975632470-60d368a613f774189902f555.jpeg)
OOM when running the simple code again in jupyter notebook
2
#16 opened about 1 year ago
by
becks2000
Issues with Auto
3
#15 opened about 1 year ago
by
Devonance
What is the different between GPTQ and QLoRA?
2
#12 opened about 1 year ago
by
Ichsan2895
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/Uq5V3aIHpSHDPyHBBvEq-.jpeg)
error when loading sucessful and prompting simple text
19
#11 opened about 1 year ago
by
joseph3553
Custom 4-bit Finetuning 5-7 times faster inference than QLora
#7 opened about 1 year ago
by
rmihaylov
Error when attempting to run.. Appears model files are missing or configuration issue
20
#6 opened about 1 year ago
by
jdc4429
cuda extension not installed
2
#5 opened about 1 year ago
by
becks2000
3bit quantization
1
#3 opened about 1 year ago
by
nbzj
GGML?
7
#2 opened about 1 year ago
by
creative420
Unfortunately I can't run on text-generation-webui
11
#1 opened about 1 year ago
by
Suoriks