DeepSeek 系列工作解读、扩展和复现。
☆726Mar 9, 2026Updated last month
Alternatives and similar repositories for unlock-deepseek
Users that are interested in unlock-deepseek are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reproduce R1 Zero on Logic Puzzle☆2,445Mar 20, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,054Feb 27, 2026Updated last month
- Simple RL training for reasoning☆3,845Dec 23, 2025Updated 3 months ago
- Fully open reproduction of DeepSeek-R1☆25,991Apr 2, 2026Updated 2 weeks ago
- 《大模型白盒子构建指南》：一个全手搓的Tiny-Universe☆4,727Feb 12, 2026Updated 2 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- minimal-cost for training 0.5B R1-Zero☆814May 14, 2025Updated 11 months ago
- ☆763Dec 23, 2025Updated 3 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆799Apr 27, 2025Updated 11 months ago
- 大模型/LLM推理和部署理论与实践☆386Jul 14, 2025Updated 9 months ago
- This is a multi agent tutorial based on the CAMEL framework, aimed at understanding how to build an Agent Society from the ground up!☆751Jan 16, 2026Updated 3 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,340Updated this week
- 大模型基础: 一文了解大模型基础知识☆7,117Dec 18, 2025Updated 4 months ago
- Hugging Vision, Hugging AGI.☆180Nov 13, 2025Updated 5 months ago
- 通过带领大家解读Transformer模型来加深对模型的理解☆241Jun 3, 2025Updated 10 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- s1: Simple test-time scaling☆6,645Jun 25, 2025Updated 9 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☆29,737Updated this week
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,644Nov 21, 2025Updated 4 months ago
- 仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理☆4,078Mar 26, 2026Updated 3 weeks ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆20,603Apr 10, 2026Updated last week
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,860Apr 6, 2026Updated last week
- Official Repo for Open-Reasoner-Zero☆2,091Jun 2, 2025Updated 10 months ago
- Fully open data curation for reasoning models☆2,246Dec 2, 2025Updated 4 months ago
- Democratizing Reinforcement Learning for LLMs☆5,439Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Building DeepSeek R1 from Scratch☆752Mar 21, 2025Updated last year
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated 11 months ago
- MLLM @ Game☆16May 12, 2025Updated 11 months ago
- 最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容是AGI/ASI的核心。☆45Feb 8, 2025Updated last year
- SGLang Kernel Wheel Index☆21Updated this week
- 基于ReAct手搓一个Agent Demo☆172Jun 28, 2025Updated 9 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, …☆13,783Updated this week
- Learning records for building a large language model from scratch☆59Jan 1, 2025Updated last year
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆70,203Apr 12, 2026Updated last week
- 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.
- llm & rl☆283Oct 24, 2025Updated 5 months ago
- Reproducing R1 for Code with Reliable Rewards☆305May 5, 2025Updated 11 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,051Updated this week
- Train transformer language models with reinforcement learning.☆18,054Updated this week
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆4,494Nov 13, 2025Updated 5 months ago
- 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）☆24,035Mar 12, 2026Updated last month
- The open source implementation of DeepSeek-R1. 开源 复现 DeepSeek-R1☆278Mar 10, 2025Updated last year