ShaohonChen / Qwen3-SmVLLinks
将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调
☆311Updated last month
Alternatives and similar repositories for Qwen3-SmVL
Users that are interested in Qwen3-SmVL are comparing it to the libraries listed below
Sorting:
- 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。☆69Updated last year
- 一些大语言模型和多模态模型的生态,主要包括跨模态搜索、投机解码、QAT量化、多模态量化、ChatBot、OCR☆188Updated 3 weeks ago
- [ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval☆220Updated 3 months ago
- A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.☆233Updated 4 months ago
- This is a user guide for the MiniCPM and MiniCPM-V series of small language models (SLMs) developed by ModelBest. “面壁小钢炮” focuses on achi…☆279Updated 2 months ago
- 多模态 MM +Chat 合集☆275Updated 2 weeks ago
- PDF解析工具:GOT的vLLM加速实现,MinerU做布局识别裁剪、GOT做表格公式解析,实现RAG中的pdf解析☆61Updated 9 months ago
- 主要记录大语言大模型(LLMs) 算法(应用)工程师多模态相关知识☆233Updated last year
- ☆65Updated last year
- ☆103Updated 11 months ago
- 【ArXiv】PDF-Wukong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling☆123Updated 3 months ago
- Repo for "VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforce…☆323Updated 2 months ago
- The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.☆236Updated this week
- ☆174Updated 7 months ago
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆125Updated 9 months ago
- A toolbox of yolo models and algorithms based on MindSpore☆145Updated 2 weeks ago
- 这是一个不基于任何框架实现的从0到1的VLM finetune(包括Pre-train和SFT)☆31Updated 2 weeks ago
- LLM101n: Let's build a Storyteller 中文版☆132Updated last year
- ☆99Updated 5 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆254Updated last year
- LLM Tokenizer with BPE algorithm☆34Updated last year
- ☆325Updated last month
- Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pret…☆696Updated last week
- Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conv…☆469Updated 5 months ago
- Deploying LLMs offline on the NVIDIA Jetson platform marks the dawn of a new era in embodied intelligence, where devices can function ind…☆100Updated last year
- 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…☆25Updated 6 months ago
- ☆51Updated 5 months ago
- Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent☆370Updated 4 months ago
- Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.☆248Updated 3 weeks ago
- Research Code for Multimodal-Cognition Team in Ant Group☆164Updated last month