yujunhuics / ReyesLinks
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。
☆26Updated 8 months ago
Alternatives and similar repositories for Reyes
Users that are interested in Reyes are comparing it to the libraries listed below
Sorting:
- Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models☆63Updated 11 months ago
- 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。☆74Updated last year
- Multimodal Open-O1 (MO1) is designed to enhance the accuracy of inference models by utilizing a novel prompt-based approach. This tool wo…☆29Updated last year
- ☆72Updated 5 months ago
- ☆186Updated 8 months ago
- This project aims to collect and collate various datasets for multimodal large model training, including but not limited to pre-training …☆58Updated 5 months ago
- A Survey of Multimodal Retrieval-Augmented Generation☆19Updated 6 months ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆38Updated last year
- [ACM MM25] The official code of "Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs"☆94Updated 2 months ago
- ☆108Updated 4 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆142Updated 6 months ago
- [ICCV2025] A Token-level Text Image Foundation Model for Document Understanding☆121Updated 2 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]☆190Updated 3 months ago
- Building a VLM model starts from the basic module.☆18Updated last year
- Pruning the VLLMs☆104Updated 10 months ago
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources☆203Updated last month
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆115Updated 11 months ago
- MLLM @ Game☆14Updated 5 months ago
- ☆95Updated last month
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆171Updated last year
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆179Updated 2 years ago
- ☆57Updated last year
- Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.☆253Updated 2 months ago
- Official code implementation of Slow Perception:Let's Perceive Geometric Figures Step-by-step☆148Updated 2 months ago
- Official PyTorch Implementation of MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced …☆86Updated 11 months ago
- Vary-tiny codebase upon LAVIS (for training from scratch)and a PDF image-text pairs data (about 600k including English/Chinese)☆86Updated last year
- The huggingface implementation of Fine-grained Late-interaction Multi-modal Retriever.☆100Updated 4 months ago
- [ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval☆228Updated 5 months ago
- [COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆274Updated 2 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆109Updated 5 months ago