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
☆33Feb 10, 2026Updated 2 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:
- pdf multimodal rag 【pdf多模态rag问答】☆28Feb 26, 2025Updated last year
- Some brief implementation of awesome attention blocks like SeNet, CBAM, DANet, A2attention and so on.☆10May 11, 2020Updated 5 years ago
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆85Jun 17, 2024Updated last year
- [KDD 2026 ADS Track] Pytorch implementation of the paper "Hi-Guard: Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasonin…☆22Jan 13, 2026Updated 3 months ago
- ☆12Aug 7, 2020Updated 5 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- 从零构建了Agent中最重要的功能-function call☆18Oct 16, 2024Updated last year
- ☆34Jun 19, 2024Updated last year
- ☆26May 30, 2024Updated last year
- 受到self-instruct启发,除了通用LLM还能做垂直领域的小LLM实现定制效果，通过GPT获得question和answer来作为训练数据☆18May 12, 2023Updated 2 years ago
- ☆11Oct 31, 2024Updated last year
- ☆12Aug 17, 2022Updated 3 years ago
- ☆10Mar 14, 2023Updated 3 years ago
- ☆24May 23, 2025Updated 11 months ago
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆13May 31, 2023Updated 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.
- ☆51Nov 3, 2025Updated 6 months ago
- ☆35Mar 2, 2025Updated last year
- [ICLR'24] Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate☆13Jun 17, 2025Updated 10 months ago
- ☆13Sep 25, 2023Updated 2 years ago
- FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models☆12Dec 21, 2025Updated 4 months ago
- AI Agent 面试知识库 100 题 | 涵盖 Agent 架构、RAG、工具使用、多 Agent、记忆、规划推理、提示工程、评估、安全对齐、生产部署、框架选型☆94Apr 24, 2026Updated 2 weeks ago
- A single Layer CNN on MIST, get an acurray of 97.24%☆11Jun 12, 2015Updated 10 years ago
- Face++ 是一款基于 Android 平台开发的创新性 AI 面相分析应用。它巧妙地将中国传统面相学理论（如“三庭五眼”和“十二宫”）与现代人工智能技术相结合，为用户提供一份专业、详尽且富有洞察力的面相分析报告☆22Jul 14, 2025Updated 9 months ago
- [NeurIPS 2025] E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization☆37Nov 3, 2025Updated 6 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- EMNLP 2024 | Style-Specific Neurons for Steering LLMs in Text Style Transfer☆13Mar 23, 2025Updated last year
- 训练一个对中文支持更好的LLaVA模型，并开源训练代码和数据。☆82Sep 6, 2024Updated last year
- Just a simple Android app that uses Rokid's CXR-M SDK to upload/sideload an APK onto your Rokid glasses over Wi-Fi. It might be hard to g…☆42Apr 9, 2026Updated last month
- [Under Review] Super4DR: 4D Radar-centric Self-supervised Odometry and Gaussian-based Map Optimization☆31Dec 11, 2025Updated 4 months ago
- 增加了indextts2的简单的界面与api调用方式☆27Oct 27, 2025Updated 6 months ago
- A Survey of LLM Alignment (SFT & RLHF), and A Survey of RLHF methods (2023~2024)☆21May 21, 2024Updated last year
- lightweighted deep learning inference service framework☆39Jun 19, 2021Updated 4 years ago
- [ICRA2024] Official implementation and Dataset of Physcal Priors Augmented Event-based 3D reconstruction☆18Jan 16, 2025Updated last year
- AI驱动的虚拟数字人直播系统，支持2D/3D数字人、TTS、ASR、唇形同步、推流、互动等模块化开发。☆24May 13, 2025Updated 11 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning☆49Mar 25, 2026Updated last month
- occlusion inpainting for unsupervised optical flow estimation☆15Aug 2, 2022Updated 3 years ago
- 一个开源的多模态 AI 搜索项目，结合 大语言模型（LLM）+ 多源搜索引擎 + 多 Agent 架构，打造新一代的智能问答式搜索体验☆17Mar 26, 2025Updated last year
- PDF Extraction Toolkit (wraps and trains LayoutLM)☆10Oct 8, 2021Updated 4 years ago
- A third-party implementation of paper《SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spell…☆14Nov 27, 2020Updated 5 years ago
- Caffe: a fast open framework for deep learning.☆14Jun 23, 2017Updated 8 years ago
- [ACL2026 Findings] "Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models"☆20Mar 25, 2025Updated last year