Spaces:

hf-accelerate
/

model-memory-usage

Running on CPU Upgrade

Only do model name translation for Llama-2 and CodeLlama

#37

by sudokien - opened Nov 10

←

Nov 10

The function translate_llama2 adds '-hf' suffix to all meta-llama models, which is incorrect. This commit fixes that.

accelerate org Nov 11

Thanks!

muellerzr changed pull request status to merged Nov 11

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment