Hugging Face's logo

notstoic
/
OPT-13B-Erebus-4bit-128g

Text Generation
Transformers
English
opt
Model card Files Community
5
notstoic commited on
Commit
80af3d4
•
1 Parent(s): aa07aa2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -1,4 +1,5 @@
1
  4-bit GPTQ quantization of https://huggingface.co/KoboldAI/OPT-13B-Erebus
 
2
  Using this fork of GPTQ: https://github.com/0cc4m/GPTQ-for-LLaMa
3
 
4
  python repos/gptq/opt.py --wbits 4 models/KoboldAI_OPT-13B-Erebus c4 --groupsize 128 --save models/KoboldAI_OPT-13B-Erebus/OPT-13B-Erebus-4bit-128g.pt
 
1
  4-bit GPTQ quantization of https://huggingface.co/KoboldAI/OPT-13B-Erebus
2
+
3
  Using this fork of GPTQ: https://github.com/0cc4m/GPTQ-for-LLaMa
4
 
5
  python repos/gptq/opt.py --wbits 4 models/KoboldAI_OPT-13B-Erebus c4 --groupsize 128 --save models/KoboldAI_OPT-13B-Erebus/OPT-13B-Erebus-4bit-128g.pt