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 8 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:
- ☆34Mar 2, 2025Updated last year
- VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction☆16Mar 26, 2026Updated 7 months ago
- Recent Advances on MLLM's Reasoning Ability☆26Apr 11, 2025Updated last year
- [ICLR 2026] Official implementation of the paper "Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs"☆26Mar 3, 2026Updated 8 months ago
- [ACL2026 Findings] "Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models"☆20Mar 25, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- This repository provides the PyTorch implementation of the paper: Anomaly Discovery in Semantic Segmentation via Distillation Comparison …☆15Apr 18, 2023Updated 3 years ago
- TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP☆10Sep 23, 2021Updated 5 years ago
- ☆12Aug 7, 2020Updated 6 years ago
- OpenVLA Lightweight Version(0.5B). It uses qwen2-0.5B and fine-tunes using mllm format, without occupying LLM's inherent tokens. It repre…☆18Jan 7, 2026Updated 10 months ago
- ☆34Updated this week
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆13May 31, 2023Updated 3 years ago
- ☆26Oct 2, 2023Updated 3 years ago
- ☆15Apr 25, 2025Updated last year
- 使用自己的tokenizer继续预训练大语言模型。☆11Jun 25, 2023Updated 3 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.
- ☆24Nov 4, 2025Updated last year
- [NeurIPS 2024] DiffSF: Diffusion Models for Scene Flow Estimation☆30Jan 9, 2025Updated last year
- [ACL'25] SocialEval: Evaluating Social Intelligence of Large Language Models☆12Oct 20, 2025Updated last year
- Official GitHub repo for Learning Normal Flow Directly from Event Neighborhoods (ICCV2025). It is an easy-to-use API for event-based norm…☆26Oct 5, 2025Updated last year
- Official implementation for "Feedback World Model Enables Precise Guidance of Diffusion Policy" (NeurIPS 2026)☆15Oct 22, 2026Updated 2 weeks ago
- ☆16Jul 1, 2026Updated 4 months ago
- ☆11Oct 31, 2024Updated 2 years ago
- ☆12Aug 17, 2022Updated 4 years ago
- [ICLR'24] Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate☆14Jun 17, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程☆11Jun 8, 2024Updated 2 years ago
- A Transformer-based framework for monocular visual odometry using multimodal RGB and pseudo-depth fusion.☆18Aug 8, 2025Updated last year
- [NeurIPS 2023] The implementation of paper "Empowering Collaborative Filtering Generalization via Principled Adversarial Contrastive Loss…☆21Feb 21, 2024Updated 2 years ago
- A repository to introduce the algorithmic information theory. You could learn what is Kolmogorov complexity and why it is important here.☆13Jul 23, 2025Updated last year
- VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs☆334Jun 18, 2026Updated 4 months ago
- ☆12Oct 12, 2024Updated 2 years ago
- ☆13Sep 25, 2023Updated 3 years ago
- ☆12Jan 18, 2026Updated 9 months ago
- 一个快速学习deepseekV3模型以及r1强化学习grpo的仓库，侧重于理解技术报告与模型设计细节，理解原理☆10Mar 21, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- pdf multimodal rag 【pdf多模态rag问答】☆30Feb 26, 2025Updated last year
- ☆66Feb 5, 2024Updated 2 years ago
- ☆41Mar 18, 2020Updated 6 years ago
- [ICML2024] "FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees" by Jiaha…☆14Sep 22, 2024Updated 2 years ago
- LDPC码的编解码python实现，并采用GPU并行加速☆14Dec 3, 2024Updated last year
- CVPR2024 highlight.☆13Oct 10, 2024Updated 2 years ago
- ☆10Apr 15, 2023Updated 3 years ago