Skip to content
View yuanxuns's full-sized avatar

Block or report yuanxuns

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Popular repositories Loading

  1. McCormick-Relaxations-in-Python McCormick-Relaxations-in-Python Public

    MCPy is a python library for McCormick relaxations with sub-gradients. This is quite useful for prototyping and testing new convex relaxation and global optimization algorithms.

    Jupyter Notebook 1

  2. RLHF-with-PPO-from-Scratch-in-Pytorch RLHF-with-PPO-from-Scratch-in-Pytorch Public

    A pytorch impementation of RLHF with PPO from scratch.

    Python

  3. DPO-in-Pytorch DPO-in-Pytorch Public

    This repository implements Direct Preference Optimization (DPO) in pytorch.

    Python

  4. Transformer-From-Scratch-in-Pytorch Transformer-From-Scratch-in-Pytorch Public

    A pytorch impementation of transformer from scratch.

    Python

  5. Improved-GRPO-From-Scratch-in-Pytorch Improved-GRPO-From-Scratch-in-Pytorch Public

    Implement an improved group relative policy optimization (GRPO) algorithms from scatch in pytorch.

    Python