KAUST-AI-INIT

VideoRLCS

Learning to Identify Critical States for Reinforcement Learning from Videos (Accepted to ICCV'23)

.github

AceGPT

Using AceGPT to evaluate our model, this code addresses the issue of the model's maximum input length limitation of 2048 by splitting the text.

Arabic-eval

Datasets and description of Arabic model evaluation task

ibex-ngrok-endpoints

I use this repo to deliver models hosted in Ibex to my colab notebooks via NGROK and singularity

orca

ORCA is a large-scale Arabic Language Understanding Evaluation Benchmark

Taqyim

Python intefrace for evaluation on chatgpt models