Libraries & frameworks
peft
huggingface/peft
A Python library for parameter-efficient fine-tuning like LoRA, adapting large pretrained models by training only small adapters.
Topics
Related projects
Soup10.5kA one-config CLI framework for fine-tuning and post-training LLMs with QLoRA, evals, and export.
ml-engineering19.7kAn open book on machine learning engineering, collecting practical guides, scripts, and troubleshooting for training and serving large models.
superduper5.3kSuperduper: End-to-end framework for building custom AI applications and agents.
MetaClaw3.5kA proxy harness for personal agents that injects skills, persists memory and meta-learns from live conversations.
second-brain-ai-assistant-course3.1kAn open-source course teaching how to build a Second Brain AI assistant with RAG, agents, fine-tuning and LLMOps.
Confucius4-TTS852Confucius4-TTS is an open multilingual, cross-lingual zero-shot text-to-speech model that clones a speaker's voice across 14 languages while preserving emotion and identity.