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。
☆22Updated 5 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 9 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。☆64Updated 10 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 10 months ago
- ☆57Updated last year
- ☆173Updated 5 months ago
- ☆101Updated last month
- Research Code for Multimodal-Cognition Team in Ant Group☆161Updated 3 weeks ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 10 months ago
- [ICCV2025] A Token-level Text Image Foundation Model for Document Understanding☆111Updated this week
- A Survey of Multimodal Retrieval-Augmented Generation☆18Updated 3 months ago
- This project aims to collect and collate various datasets for multimodal large model training, including but not limited to pre-training …☆53Updated 2 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory☆164Updated 2 weeks ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆138Updated 3 months ago
- Our 2nd-gen LMM☆34Updated last year
- ☆29Updated 11 months ago
- ☆28Updated last year
- ☆67Updated 2 months ago
- [ACM MM25] The official code of "Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs"☆83Updated 3 weeks ago
- ☆87Updated 3 weeks ago
- Official code implementation of Slow Perception:Let's Perceive Geometric Figures Step-by-step☆131Updated this week
- [ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval☆209Updated 2 months ago
- The huggingface implementation of Fine-grained Late-interaction Multi-modal Retriever.☆93Updated 2 months ago
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆152Updated last year
- Pruning the VLLMs☆99Updated 7 months ago
- 将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调☆128Updated this week
- Official PyTorch Implementation of MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced …☆79Updated 8 months ago
- [COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆244Updated 2 months ago
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆116Updated 8 months ago
- Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines☆125Updated 8 months ago
- Official Repository of MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations☆90Updated last year