peft

An open, interactive knowledge graph of modern AI — 123 concepts from tokens & attention to LoRA, DPO, reasoning models, and agents, with typed connections. Fully offline, zero dependencies. Built on the Open Knowledge Format.

A self-service platform that enables users to fine-tune Large Language Models (LLMs) for specific tasks.

Automate Microsoft Account OAuth registration and token imports with this Chrome extension for the Microsoft Account Manager API.

내 GPU로 이 모델을 어떻게 파인튜닝하지? 학습 VRAM·기법·데이터·시간을 공식과 함께 계산하는 정적 웹 도구 (100% 브라우저, MIT)

Automated High-Energy Control Assessment system using Florence-2 VLM + Llama 3 LLM for construction site hazard detection. Research project at IIT Madras. Abstract shortlisted at ICONS 2026 (CIB W099).

FastAPI-based AI chat app using Hugging Face LLM adapters, local inference, and a simple web UI.

Fine tuned qwen llm using qloRa for commentary generation and generating audio using edge-tts.

End-to-end platform for LLM post-training. Dataset versioning, training orchestration, model registry, and evaluation pipelines for teams shipping specialized models.