Pinned Loading

1. nanoRL nanoRL Public

   Minimal, single-file implementations of RL algorithms applied to LLMs, including REINFORCE (and RLOO), PPO and GRPO.

   Python

2. llm-decoding llm-decoding Public

   Prompt Lookup Speculative Decoding vs Standard Decoding for LLMs

   Python

3. LLAMBO-FT LLAMBO-FT Public

   Fine-tuned LLMs for Bayesian Optimization

   Python

4. rapid-inpainting rapid-inpainting Public

   MEng Project - Rapid Inpainting for Virtual Shoe Try-On

   Python

5. logsim logsim Public

   Forked from WeixuanZ/logsim

   Logic Simulator

   Python

6. jeevs-jpeg jeevs-jpeg Public

   Personal photography portfolio

   HTML