#Dpo
Showing 18 of 18 repositories tagged #dpo, ranked by stars
Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!
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。
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
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.
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
An Efficient "Factory" to Build Multiple LoRA Adapters
A Survey of Direct Preference Optimization (DPO)
逐行对照 MiniMind 源码精读、并延伸到大模型技术体系的中文学习笔记 —— 预训练 / SFT / DPO / PPO / GRPO、训练机制、MiniMind2→3 版本对照、真实实验证据。
[ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
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
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Curated, opinionated index of post-R1 LLM × Reinforcement Learning. Many deep-dive blog posts cross-linked to many papers — GRPO, DAPO, DPO, PPO, RLHF, GSPO, CISPO, VAPO, Reward Modeling, MoE RL stability, Verifier-Free RL, Training-Free RL, Agentic RL, DeepSeek-R1 reproduction.
We introduce the direct document relevance optimization (DDRO) for training a pairwise ranker model. DDRO encourages the model to focus on document-level relevance during generation
AutoAdapt: An Automated Domain Adaptation Framework for Large Language Models