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。)
☆811Mar 13, 2025Updated last year
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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepLiterature: A fully open-source intelligent research assistant that integrates search, code execution, link resolution, and informati…☆105Mar 19, 2025Updated last year
- 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)☆11May 8, 2025Updated last year
- ☆22Aug 1, 2025Updated 11 months ago
- This repository contains code and data for the paper "TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured T…☆30Jun 12, 2025Updated last year
- adds Sequence Parallelism into LLaMA-Factory☆607Feb 5, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆765Dec 23, 2025Updated 7 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)☆320Aug 8, 2024Updated last year
- Building DeepSeek R1 from Scratch☆782Mar 21, 2025Updated last year
- A Next-Generation Training Engine Built for Ultra-Large MoE Models☆5,163Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,848Jul 14, 2026Updated last week
- Large Language Model in Action☆342Jan 28, 2025Updated last year
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,325Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆452Oct 23, 2025Updated 9 months ago
- [ACL 2025 Demo] Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths☆513Mar 9, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- DeepSeek 系列工作解读、扩展和复现。☆733Mar 9, 2026Updated 4 months ago
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆73,508Updated this week
- 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…☆14,946Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,599Updated this week
- A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.☆3,139Updated this week
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,585Dec 15, 2025Updated 7 months ago
- Democratizing Reinforcement Learning for LLMs☆5,731Updated this week
- Official Repo for Open-Reasoner-Zero☆2,096Jun 2, 2025Updated last year
- Fully open reproduction of DeepSeek-R1☆26,414Apr 2, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 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、…☆6,647Oct 24, 2024Updated last year
- minimal-cost for training 0.5B R1-Zero☆816May 14, 2025Updated last year
- O1 Replication Journey☆2,001Jan 14, 2025Updated last year
- Simple RL training for reasoning☆3,870Dec 23, 2025Updated 7 months ago
- PDF2MD是一个高效的PDF到Markdown转换工具，旨在帮助用户轻松将PDF文档转换为Markdown格式，便于编辑、分享和发布。通过简洁易用的界面和强大的转换功能，PDF2MD成为内容创作者、研究人员和开发者的得力助手。☆184Oct 11, 2025Updated 9 months ago
- ☆985Feb 7, 2025Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,654Updated this week
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,848Jan 17, 2025Updated last year
- Awesome Reasoning LLM Tutorial/Survey/Guide☆2,485Apr 6, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆157Dec 24, 2024Updated last year
- ☆26Jul 2, 2026Updated 3 weeks ago
- [ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents☆51Feb 2, 2026Updated 5 months ago
- 📐 [CVPR 2026] GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models☆18Apr 1, 2026Updated 3 months ago
- BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）☆8,277Oct 16, 2024Updated last year
- Making large AI models cheaper, faster and more accessible☆41,427Jul 13, 2026Updated last 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.☆8,743Updated this week