An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案，包含从训练到推理的完整代码和脚本，以及实践中积累一些经验和结论。)
☆797Mar 13, 2025Updated 11 months ago
Alternatives and similar repositories for DeepSeek-671B-SFT-Guide
Users that are interested in DeepSeek-671B-SFT-Guide are comparing it to the libraries listed below
Sorting:
- DeepLiterature: A fully open-source intelligent research assistant that integrates search, code execution, link resolution, and informati…☆101Mar 19, 2025Updated 11 months ago
- A supervised fine-tuning method for controllable reasoning length in large language models (一种通过有监督微调实现大语言模型思考长度可控的方法)☆10May 8, 2025Updated 9 months ago
- adds Sequence Parallelism into LLaMA-Factory☆604Feb 5, 2026Updated last month
- ☆762Dec 23, 2025Updated 2 months ago
- [ACL 2025 Demo] Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths☆513May 23, 2025Updated 9 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆451Oct 23, 2025Updated 4 months ago
- A Next-Generation Training Engine Built for Ultra-Large MoE Models☆5,087Updated this week
- Building DeepSeek R1 from Scratch☆747Mar 21, 2025Updated 11 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,084Updated this week
- Large Language Model in Action☆342Jan 28, 2025Updated last year
- DeepSeek 系列工作解读、扩展和复现。☆699Mar 29, 2025Updated 11 months ago
- 雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆315Aug 8, 2024Updated last year
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,586Updated this week
- minimal-cost for training 0.5B R1-Zero☆808May 14, 2025Updated 9 months ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆156Dec 24, 2024Updated last year
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆67,659Updated this week
- 🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.☆7,587Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL,…☆12,820Updated this week
- [NAACL 2025] Representing Rule-based Chatbots with Transformers☆23Feb 9, 2025Updated last year
- Fully open reproduction of DeepSeek-R1☆25,910Nov 24, 2025Updated 3 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,519Updated this week
- Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、…☆6,638Oct 24, 2024Updated last year
- Official Repo for Open-Reasoner-Zero☆2,087Jun 2, 2025Updated 9 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,833Jan 17, 2025Updated last year
- ☆978Feb 7, 2025Updated last year
- A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval☆13,460Feb 25, 2026Updated last week
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,534Dec 15, 2025Updated 2 months ago
- O1 Replication Journey☆1,999Jan 14, 2025Updated last year
- A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.☆2,436Feb 25, 2026Updated last week
- Democratizing Reinforcement Learning for LLMs☆5,167Updated this week
- Awesome Reasoning LLM Tutorial/Survey/Guide☆2,307Oct 14, 2025Updated 4 months ago
- Official code implementation for the ACL 2025 paper: 'CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis'☆32May 19, 2025Updated 9 months ago
- YiZhao: A 2TB Open Financial Corpus. Data and tools for generating and inspecting YiZhao, a safe, high-quality, open-source bilingual fin…☆38Jul 11, 2025Updated 7 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆23,905Updated this week
- 动手学Ollama，CPU玩转大模型部署，在线阅读地址：https://datawhalechina.github.io/handy-ollama/☆2,241Jan 15, 2026Updated last month
- ☆18Sep 5, 2024Updated last year
- Simple RL training for reasoning☆3,830Dec 23, 2025Updated 2 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆2,881Updated this week
- BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）☆8,281Oct 16, 2024Updated last year