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, 2025

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

AI21 org Jul 6, 2025

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, 2025

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