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。
☆14Updated 4 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☆62Updated 7 months ago
- ☆57Updated last year
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆117Updated 6 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆131Updated 2 months ago
- The official repo for “TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding”.☆40Updated 9 months ago
- This project aims to collect and collate various datasets for multimodal large model training, including but not limited to pre-training …☆48Updated last month
- Multimodal Open-O1 (MO1) is designed to enhance the accuracy of inference models by utilizing a novel prompt-based approach. This tool wo…☆29Updated 8 months ago
- Official PyTorch Implementation of MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced …☆78Updated 7 months ago
- A Survey of Multimodal Retrieval-Augmented Generation☆18Updated 2 months ago
- ☆81Updated last week
- Research Code for Multimodal-Cognition Team in Ant Group☆151Updated last month
- ☆29Updated 10 months ago
- A Token-level Text Image Foundation Model for Document Understanding☆96Updated last month
- Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆229Updated last month
- 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。☆61Updated 9 months ago
- MMR1: Advancing the Frontiers of Multimodal Reasoning☆160Updated 3 months ago
- The official code of "Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs"☆75Updated last month
- Official code implementation of Slow Perception:Let's Perceive Geometric Figures Step-by-step☆129Updated 4 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory☆128Updated this week
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆104Updated 3 weeks ago
- Vary-tiny codebase upon LAVIS (for training from scratch)and a PDF image-text pairs data (about 600k including English/Chinese)☆84Updated 9 months ago
- ☆181Updated last year
- MLLM @ Game☆14Updated last month
- MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering. A comprehensive evaluation of multimodal large model multilingua…☆59Updated last month
- Official repository of MMDU dataset☆92Updated 8 months ago
- 【ArXiv】PDF-Wukong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling☆120Updated 2 weeks ago
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆44Updated 11 months ago
- ☆85Updated last year
- Pruning the VLLMs☆96Updated 6 months ago
- Official Repository of MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations☆83Updated 11 months ago