Spaces:

open-llm-leaderboard
/

open_llm_leaderboard

Running on CPU Upgrade

App Files Files Community

781

Help

#641

by Aarifkhan - opened Mar 21

Discussion

Aarifkhan

Mar 21

My models Precision is F32 what should I select

clefourrier

Open LLM Leaderboard org Mar 25

Hi!
I'd suggest bfloat16, as it's got the same range as float32 (but a lower precision), and should convert well. (See more info on the wikipedia page).

clefourrier changed discussion status to closed Mar 25

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