Pinned Loading

1. time_llm time_llm Public

   A transformer coded from scratch. Designed to make LLMs special-token aware

   Python

2. dpo_sample dpo_sample Public

   Implementation of DPO for RLHF pipeline. Just upload a CSV and let the model train the rest.

   Python 1

3. Gymnasium-Robotics Gymnasium-Robotics Public

   Forked from bstadie/Gymnasium-Robotics

   Personal environments added to experiment with robustness of vision encoders for visuomotor learning. A collection of robotics simulation environments for reinforcement learning

   Python 1

4. curiosity_redteam curiosity_redteam Public

   Forked from Improbable-AI/curiosity_redteam

   Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizXgXU)

   Jupyter Notebook

5. Metaworld Metaworld Public

   Forked from Farama-Foundation/Metaworld

   Modifications to the environments to enable visual data collection more easily. Collections of robotics environments geared towards benchmarking multi goal reinforcement learning

   Python

6. jax_demo jax_demo Public

   (WIP) This repo is for those who have experience in deep learning with torch, and want to learn a lesser known but still powerful library JAX

   Jupyter Notebook