Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Adapting pretrained models: PEFT/LoRA, instruction tuning, RLHF, DPO and preference alignment.
Signals: fine-tuning, finetuning, lora, peft, qlora, rlhf, dpo, instruction-tuning
283 results
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Textbook on reinforcement learning from human feedback
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
ACP adapter for pi coding agent
:zap: The most powerful open source tweaker on GitHub for fine-tuning Windows 10 & Windows 11
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
🎓 系统性大语言模型构建课程｜🛠️ 覆盖预训练数据工程、Tokenizer、Transformer、MoE、GPU 编程 (CUDA/Triton)、分布式训练、Scaling Laws、推理优化及对齐 (SFT/RLHF/GRPO)｜🚀 6 个渐进式作业 + 代码驱动，建立 LLM 全栈认知体系
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Train Large Language Models on MLX.
A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.
An alignment auditing agent capable of quickly exploring alignment hypothesis
Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.
Training/Fine-tuning at the speed of light
One-click Portable Windows installation of 'AI-Toolkit by Ostris'
Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
ONLYOFFICE DocSpace is a room-based collaborative platform which allows organizing a clear file structure depending on users' needs or project goals. Flexible access permissions and user roles allow fine-tuning the access to the whole space or separate rooms.
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
AirLLM 70B inference with single 4GB GPU
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
24,520 repositories in the index in total.
