dpo

Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

Align Anything: Training All-modality Model with Feedback

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning NLP 저장소입니다.

Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.

A framework for agentic tool use training with reinforcement learning

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach

基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了自定义的 SFTTrainer/DPOTrainer/TRPOTrainer用于训练，其次，项目还调用各种知识库工具（neo4j, milvus, LDA, 等）进行自动化训练数据生成。另外，使用 vllm 用于推理和部署训好的模型, 该模型会通过 vllm API 来接入一个基于 embedder + Reranker 的 RAG 系统。另外还参考 MDAgents 论文实现了一个多智能体会诊系统，同样也支持 vllm api 接入。

A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using the response. A RAG system is build upon the tuned qwen2, using Prompt-Template + Tool-Use + Chroma embedding database + LangChain

Powerful no-code LLM fine-tuner: upload data → train → deploy in minutes. Unsloth 2-5× acceleration · QLoRA/DPO/RLHF/PPO/ORPO · Reward Model training · GGUF export · vLLM inference · BLEU/ROUGE/BERTScore · full CLI · Heretic Mode to unlock full model potential

Synthetic data for fine tuning LLM

Interview prep for LLM post-training, ML, system design, and coding — organized by career path.

A fine-tuning SDK — any open model, any harness, any method. 12 training methods behind one argument; pure-stdlib core.

[ACL 2026] CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy

Tool-native dataset generation skill for Codex, Claude Code, and Antigravity with SFT/DPO pipelines, verification, deduplication, and flexible export.

A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.