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

e63ad76

•

1 Parent(s): 137e2d4

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -29,9 +29,9 @@ TBD
 ## Compatibility
-The model has been tested with GPTQ for LLaMA on 2x24 VRAM GPUs.
-Exllama works and it is the recommended way to use it now.

 ## Compatibility
+Exllama works 2x24 VRAM GPUs and it is the recommended way to use it now. It even can do 16K! context with high alpha values and NTK Alpha.
+The model has been tested as well with GPTQ for LLaMA.