Building DeepSeek R1 from Scratch
☆753Mar 21, 2025Updated last year
Alternatives and similar repositories for train-deepseek-r1
Users that are interested in train-deepseek-r1 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A straightforward method for training your LLM, from downloading data to generating text.☆565Aug 3, 2025Updated 9 months ago
- A Straightforward, Step-by-Step Implementation of a Video Diffusion Model☆82Aug 18, 2025Updated 8 months ago
- Implementation of a GPT-4o like Multimodal from Scratch using Python☆77Apr 4, 2025Updated last year
- 该系列的目的是让读者可以在基础的pytorch上，不依赖任何其他现成的外部库，从零开始理解并实现一个大语言模型的所有组成部分，以及训练微调代码，因此读者仅需python，pytorch和最基础深度学习背景知识即可。☆387Aug 28, 2025Updated 8 months ago
- 一个手把手教你从零开始编写GPT并训练大语言模型的教程☆100Jan 20, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- In this blog, we will build a small scale text-to-video model from scratch. We will input a text prompt, and our trained model will gener…☆226Jun 23, 2024Updated last year
- DeepSeek 系列工作解读、扩展和复现。☆729Mar 9, 2026Updated last month
- An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to infer…☆806Mar 13, 2025Updated last year
- Fully open reproduction of DeepSeek-R1☆26,016Apr 2, 2026Updated last month
- Implementation of 12 AI agents evaluation techniques☆43Jul 31, 2025Updated 9 months ago
- ☆134Feb 17, 2025Updated last year
- Maximizing the Performance of a Simple RAG using RL☆92Mar 20, 2025Updated last year
- ☆763Dec 23, 2025Updated 4 months ago
- Fetch arxiv data to LLM-friendly text☆132Feb 18, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Large Language Model in Action☆345Jan 28, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,091Feb 27, 2026Updated 2 months ago
- LLMs-from-scratch项目中文翻译☆2,598Apr 19, 2026Updated 2 weeks ago
- Awesome Reasoning LLM Tutorial/Survey/Guide☆2,396Apr 6, 2026Updated last month
- 🧑🚀 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.☆8,228Updated this week
- LLaMA 3 is one of the most promising open-source model after Mistral, we will recreate it's architecture in a simpler manner.☆207Aug 23, 2024Updated last year
- Learning records for building a large language model from scratch☆59Jan 1, 2025Updated last year
- Implementation of all RL algorithms in a simpler way☆1,554Aug 29, 2025Updated 8 months ago
- Reproduce R1 Zero on Logic Puzzle☆2,448Mar 20, 2025Updated last year
- 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.
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,441Updated this week
- diagnosis_zero, R1 Zero reproduce on disease diagnosis☆34Jul 24, 2025Updated 9 months ago
- Simple RL training for reasoning☆3,853Dec 23, 2025Updated 4 months ago
- Official Repo for Open-Reasoner-Zero☆2,093Jun 2, 2025Updated 11 months ago
- All-in-one benchmarking platform for evaluating LLM.☆15Nov 12, 2025Updated 5 months ago
- 这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。☆836Feb 18, 2025Updated last year
- 🚀 「大模型」2小时完全从0训练64M的小参数LLM！🌏 Train a 64M-parameter LLM from scratch in just 2h!☆48,747May 1, 2026Updated last week
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,669Nov 21, 2025Updated 5 months ago
- Open replication of DeepSeek R1 for text-to-graph extraction.☆102Jan 31, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆14,032Updated this week
- Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.☆7,813Nov 19, 2025Updated 5 months ago
- Democratizing Reinforcement Learning for LLMs☆5,479Updated this week
- Fully open data curation for reasoning models☆2,257Dec 2, 2025Updated 5 months ago
- 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程☆30,252Apr 24, 2026Updated 2 weeks ago
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆70,969Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,046Apr 30, 2026Updated last week