yujunhuics / Reyes
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。
☆11Updated 2 months ago
Alternatives and similar repositories for Reyes:
Users that are interested in Reyes are comparing it to the libraries listed below
- Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models☆60Updated 5 months ago
- Multimodal Open-O1 (MO1) is designed to enhance the accuracy of inference models by utilizing a novel prompt-based approach. This tool wo…☆29Updated 6 months ago
- The official repo for “TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding”.☆38Updated 6 months ago
- ☆56Updated last year
- 【ArXiv】PDF-Wukong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling☆115Updated 5 months ago
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆115Updated 4 months ago
- This project aims to collect and collate various datasets for multimodal large model training, including but not limited to pre-training …☆37Updated 6 months ago
- A Token-level Text Image Foundation Model for Document Understanding☆87Updated 3 weeks ago
- Vary-tiny codebase upon LAVIS （for training from scratch）and a PDF image-text pairs data (about 600k including English/Chinese)☆79Updated 6 months ago
- ☆29Updated 7 months ago
- ☆15Updated 3 weeks ago
- Official PyTorch Implementation of MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced …☆66Updated 5 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。☆54Updated 7 months ago
- ☆27Updated 11 months ago
- Research Code for Multimodal-Cognition Team in Ant Group☆141Updated 9 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory☆84Updated last week
- ☆82Updated 11 months ago
- Official code implementation of Slow Perception:Let's Perceive Geometric Figures Step-by-step☆123Updated 2 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆99Updated last month
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆142Updated 10 months ago
- GOT的vLLM加速实现 并结合 MinerU 实现RAG中的pdf 解析☆55Updated 5 months ago
- Building a VLM model starts from the basic module.☆14Updated last year
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 7 months ago
- Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆155Updated last week
- Official Repository of MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations☆76Updated 9 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆37Updated 4 months ago
- The official implementation of RAR☆85Updated last year
- Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines☆120Updated 5 months ago
- MMR1: Advancing the Frontiers of Multimodal Reasoning☆153Updated last month
- The proposed simulated dataset consisting of 9,536 charts and associated data annotations in CSV format.☆22Updated last year