Repositories
alex000kim repositories
One RL training loop that runs CartPole on a laptop and disaggregated async RLVR on a GPU cluster. About 1,800 lines across 7 files. No Ray, no TRL, no DeepSpeed. It's small enough to read in an afternoon, and it's meant to be forked, not imported.
The best ChatGPT that $100 can buy.
NLP webinar materials
Notebooks using the Hugging Face libraries 🤗
Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier
Examples and guides for using the OpenAI API
Protein 3D structure prediction pipeline
Compressed Video Action Recognition
QLoRA: Efficient Finetuning of Quantized LLMs
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 16+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
A self-hosted, secure code execution sandbox for LLM agents deployed on your cloud infrastructure using SkyPilot. Built on llm-sandbox for multi-language code execution.