Panchovix
/

LLaMA-2-70B-GPTQ-transformers4.32.0.dev0

Text Generation

text-generation-inference

Model card Files Files and versions Community

Panchovix commited on Jul 19, 2023

Commit

807e81c

•

1 Parent(s): 3841e41

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -31,7 +31,7 @@ TBD
 The model has been tested with GPTQ for LLaMA on 2x24 VRAM GPUs.
-It DOESN'T work on exllama/exllama_hf.


31
32	The model has been tested with GPTQ for LLaMA on 2x24 VRAM GPUs.
33
34	+ Exllama works and it is the recommended way to use it now.
35
36
37