2025.01：从零到一实现了一个多模态大模型，并命名为Reyes（睿视），R：睿，eyes：眼。Reyes的参数量为8B，视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct，Reyes也通过一个两层MLP投影层连接视觉编码器与语言模型。2026.01：reyes-0.6B
☆34Feb 10, 2026Updated 7 months ago
Alternatives and similar repositories for Reyes
Users that are interested in Reyes are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆93May 20, 2025Updated last year
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆93Jun 17, 2024Updated 2 years ago
- ☆34Mar 2, 2025Updated last year
- ☆15Apr 25, 2025Updated last year
- ☆19Dec 6, 2023Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ACL2026 Findings] "Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models"☆20Mar 25, 2025Updated last year
- OpenVLA Lightweight Version(0.5B). It uses qwen2-0.5B and fine-tunes using mllm format, without occupying LLM's inherent tokens. It repre…☆19Jan 7, 2026Updated 8 months ago
- The use of multimodal large model technology enables automatic generation of web scraping code. 使用多模态大模型技术实现了爬虫代码自动生成☆22Jan 7, 2025Updated last year
- ☆12Aug 17, 2022Updated 4 years ago
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆13May 31, 2023Updated 3 years ago
- [ICLR'24] Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate☆14Jun 17, 2025Updated last year
- ☆20May 14, 2024Updated 2 years ago
- ☆24Nov 4, 2025Updated 10 months ago
- [NeurIPS 2023] The implementation of paper "Empowering Collaborative Filtering Generalization via Principled Adversarial Contrastive Loss…☆21Feb 21, 2024Updated 2 years 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.
- ☆31May 13, 2024Updated 2 years ago
- ☆11Oct 31, 2024Updated last year
- [ICML2024] "FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees" by Jiaha…☆14Sep 22, 2024Updated 2 years ago
- BetterNet is a state-of-the-art deep learning model for accurate and efficient polyp segmentation in medical images. It combines Efficien…☆14May 8, 2024Updated 2 years ago
- ☆65Feb 5, 2024Updated 2 years ago
- Enhancing Retrieval and Managing Retrieval: 4-Module Synergy☆23Dec 7, 2024Updated last year
- ☆13Sep 25, 2023Updated 3 years ago
- pdf multimodal rag 【pdf多模态rag问答】☆30Feb 26, 2025Updated last year
- Creating Custom Action Recognition Model using TensorFlow (CNN + LSTM)☆12Feb 22, 2023Updated 3 years 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.
- ☆16Aug 25, 2021Updated 5 years ago
- ☆16Feb 20, 2024Updated 2 years ago
- A survey on MM-LLMs for long video understanding: From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long…☆25Sep 12, 2025Updated last year
- [Official] [IROS 2024] A goal-oriented planning to lift VLN performance for Closed-Loop Navigation: Simple, Yet Effective☆27Apr 4, 2024Updated 2 years ago
- [CVPR2025] VDocRAG: Retirval-Augmented Generation over Visually-Rich Documents☆67May 26, 2025Updated last year
- On solutions to the problem of Event Collapse in Motion Compensation frameworks☆15Jan 21, 2023Updated 3 years ago
- ☆18Apr 23, 2025Updated last year
- An unnecessarily tiny and minimal implementation of GPT-2 in NumPy.☆11Feb 12, 2023Updated 3 years ago
- 天池Better Synth多模态大模型数据合成挑战赛-打赢baseline就算成功方案☆30Oct 30, 2025Updated 10 months ago
- 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.
- [NeurIPS-W 2025] Official Implementation of "Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning"☆73Jul 1, 2025Updated last year
- ☆10Apr 15, 2023Updated 3 years ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆38Sep 9, 2024Updated 2 years ago
- [ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"☆268Apr 14, 2025Updated last year
- ☆14Aug 31, 2023Updated 3 years ago
- FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models☆15Jul 14, 2026Updated 2 months ago
- lightweighted deep learning inference service framework☆38Jun 19, 2021Updated 5 years ago