A fine-tuning SDK — any open model, any harness, any method. 12 training methods behind one argument; pure-stdlib core.
Related
0xwilliamortiz/andrej-karpathy-skills: Behavioral guardrails for Claude Code, distilled from Andrej Karpathy's field notes on where LLMs go wrong when they write software.
Behavioral guardrails for Claude Code, distilled from Andrej Karpathy's field notes on where LLMs go wrong when they write software.
taovietducofficial/ITLR-Fullstack-Recommender-RAG: Hybrid recommender system + RAG chatbot for IT courses (FastAPI + Express/TS + PostgreSQL), with an independent Data Lakehouse module (Spark/Kafka/dbt/Trino) and full CI/CD
Hybrid recommender system + RAG chatbot for IT courses (FastAPI + Express/TS + PostgreSQL), with an independent Data Lakehouse module (Spark/Kafka/dbt/Trino) and full CI/CD
OpenImagingLab/RealVDeblur: RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring