Panchovix
/

Venus-120b-v1.0-4.25bpw-h6-exl2

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Panchovix commited on Nov 27, 2023

Commit

790fc86

•

1 Parent(s): d39a332

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ tags:
 ---
 4.25 bpw/bits exl2 quantization of [Venus-120b](https://huggingface.co/nsfwthrowitaway69/Venus-120b-v1.0), using the measurement.json and dataset posted in the model page.
-This size lets it being able to use CFG on 72GB VRAM. (use 21,21,21 for gpu split)
 # Original model card

 ---
 4.25 bpw/bits exl2 quantization of [Venus-120b](https://huggingface.co/nsfwthrowitaway69/Venus-120b-v1.0), using the measurement.json and dataset posted in the model page.
+This size lets it being able to use CFG on 72GB VRAM. (use 20,21.5,21.5 for gpu split)
 # Original model card