Fine-tuning Tools

InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention

The repository has collected a batch of noteworthy MLSys bloggers (Algorithms/Systems)

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

电子鹦鹉 / Toy Language Model

SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.