Tiny-R2: A hybrid architecture integrating SWA, CSA, HCA, mHC, and DSMoE under the DeepSeek V4 design paradigm, enabling single-GPU OPD post-training.
☆47May 30, 2026Updated 2 months ago
Alternatives and similar repositories for Tiny-R2
Users that are interested in Tiny-R2 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆22Mar 1, 2026Updated 5 months ago
- Data and code for ACL 2026 Paper "Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems…☆19Apr 30, 2026Updated 3 months ago
- dUltra: Ultra-Fast Diffusion Large Language Models via Reinforcement Learning☆17Jul 11, 2026Updated last month
- DeepSeek-V4 Lecture☆27Aug 10, 2026Updated 2 weeks ago
- ☆49Feb 10, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Reasoning and Tool-use Compete in Agentic RL: From Quantifying Interference to Disentangled Tuning☆33May 7, 2026Updated 3 months ago
- 百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本☆49Aug 27, 2023Updated 2 years ago
- [IJCV 2026] Official implementation of the paper “CMPF: Harmonizing Cross-Model Prior Fusion for Open-Vocabulary Segmentation”☆26Jun 15, 2025Updated last year
- 本项目是一个基于LangChain构建的多Agent系统，结合Streamlit实现的Web界面，能够根据用户输入进行网络搜索并提供旅游相关的聊天服务。此外，该系统还具备基于本地知识库的推销功能，为用户提供个性化的旅游产品推荐。☆15Apr 20, 2025Updated last year
- 南京大学《计算传播与广告》课程☆17Jan 16, 2016Updated 10 years ago
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe☆57Jun 10, 2026Updated 2 months ago
- Pretrain、Posttrain、RAG、Agent等大模型相关的基础项目合集☆39Dec 7, 2025Updated 8 months ago
- Code for "Multi-level Relevance Document Identifier Learning for Generative Retrieval". ACL 2025.☆24Nov 5, 2025Updated 9 months ago
- ☆13Mar 24, 2024Updated 2 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- MemOCR: an OCR-driven visual memory agent.☆33May 17, 2026Updated 3 months ago
- TensorRT for RefineNet Segmentation☆12Apr 27, 2021Updated 5 years ago
- PyTorch implementation of Language model compression with weighted low-rank factorization☆14Jun 28, 2023Updated 3 years ago
- awesome LLM papers！ 🚀 🚀 🚀☆49Jul 3, 2025Updated last year
- [ACL'26 Oral] AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting R…☆45Mar 1, 2026Updated 5 months ago
- official code for Dynamic Smooth Label Assignment☆12Oct 5, 2022Updated 3 years ago
- (ACL'2023) MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning☆36Aug 8, 2024Updated 2 years ago
- The code for the paper, 'Meta-Curvature, Eunbyung Park and Junier Oliver, NeurIPS 2019'☆11Jan 20, 2020Updated 6 years ago
- ☆13Jul 22, 2024Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- PyTorch code for the CVPR'23 paper: "ConStruct-VL: Data-Free Continual Structured VL Concepts Learning"☆14Feb 5, 2024Updated 2 years ago
- [ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents☆144Jul 14, 2026Updated last month
- ☆15Nov 13, 2022Updated 3 years ago
- Code repository for the ICML 2026 Oral paper "Characterizing, Evaluating, and Optimizing Complex Reasoning".☆19Jun 21, 2026Updated 2 months ago
- [ICML 2022 Spotlight] Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks☆11May 21, 2023Updated 3 years ago
- [KDD 2026] "Breaking Information Cocoons: A Hyperbolic Graph-LLM Framework for Exploration and Exploitation in Recommender Systems"☆16Jan 29, 2025Updated last year
- Code for the paper "A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders"☆16Dec 28, 2025Updated 7 months ago
- ☆51May 9, 2026Updated 3 months ago
- 使用Flutter开发的一款App，主要功能是日程管理，根据优先级进行划分，设置时间提醒☆11Oct 29, 2018Updated 7 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Gated Pretrained Transformer model for robust denoised sequence-to-sequence modelling☆10May 29, 2021Updated 5 years ago
- Official implementation of the paper "Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering"☆20Jun 22, 2025Updated last year
- ☆19Feb 4, 2025Updated last year
- Using TensorRT accelerate Segformer.☆11Oct 6, 2023Updated 2 years ago
- Implementation of " TraVeLGAN: Image-to-image Translation by Transformation Vector Learning " CVPR 2019 https://arxiv.org/abs/1902.09631☆12Apr 4, 2020Updated 6 years ago
- During my research I usually like to visuallize and understand clearly how some papers/models work. In this repository I will create some…☆12Apr 7, 2022Updated 4 years ago
- Implementation of Pix2Seq in PyTorch☆10Feb 3, 2022Updated 4 years ago