facebookresearch / facebookresearch/perception_models

Tutorial on how to install Perception-LM locally

Open
#1 1 comment 7 reactions 0 assignees View on GitHub
PLM tutorial
Dominant language
Jupyter Notebook
Stars
2.4k
Forks
162
PR merge metrics
No merged PRs in 30d

Description

This is not an issue. Thank you for this amazing model! Here is a tutorial on how to install and run locally the Perception-LM 3B (8B) model on a Linux Ubuntu machine:

https://www.youtube.com/watch?v=RUsM04Q5YH0

Perception-LM 3B works well on NVIDIA 3090 GPU. However, Perception-LM 8B reports "CUDA out of memory". Probably needs 32GB VRAM or more.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.