ai21labs
/

AI21-Jamba-Mini-1.7-FP8

compressed-tensors

Model card Files Files and versions

aligning the name of the model, adding bullet points to further documentation

#6

by Motit - opened Jul 6

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

Motit

AI21 org Jul 6

changing the name of the model to Jamba Mini 1.7-FP8, adding bullet points to further documentation

aligning the name of the model, adding bullet points to further documentation6b4b1d5c

remove "...to the GPU in BF16 precision"3e824c69

Delete "In half precision (FP16/BF16)"40ed399b

remove remove this line torch_dtype=torch.bfloat16, and remove Jamba Mini 1.7-FP8 is too large to fit on a single 80GB GPU, so you'll need at least 2 such GPUs.12dda212

asafgardin changed pull request status to merged Jul 6

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