MonolithFoundation / Bumblebee
A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.
☆37Updated 7 months ago
Alternatives and similar repositories for Bumblebee:
Users that are interested in Bumblebee are comparing it to the libraries listed below
- ☆29Updated 8 months ago
- Chinese CLIP models with SOTA performance.☆55Updated last year
- Our 2nd-gen LMM☆33Updated 11 months ago
- ☆56Updated last year
- ☆67Updated last year
- Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models☆60Updated 6 months ago
- ☆78Updated last year
- 基于baichuan-7b的开源多模态大语言模型☆73Updated last year
- ☆27Updated 6 months ago
- SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama: https://arxiv.org/abs/2408.09333v2☆119Updated 5 months ago
- ☆28Updated 11 months ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- A Token-level Text Image Foundation Model for Document Understanding☆91Updated this week
- Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines☆123Updated 6 months ago
- LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.☆38Updated 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 7 months ago
- Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM☆100Updated 11 months ago
- Repository for 23'MM accepted paper "Curriculum-Listener: Consistency- and Complementarity-Aware Audio-Enhanced Temporal Sentence Groundi…☆49Updated last year
- ☆173Updated 3 months ago
- Search, organize, discover anything!☆49Updated last year
- Empirical Study Towards Building An Effective Multi-Modal Large Language Model☆22Updated last year
- 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力，接近gpt4o、claude-3.5-sonnet的识别水平！☆22Updated 9 months ago
- ☆17Updated last year
- 研究GOT-OCR-项目落地加速，不限语言☆60Updated 6 months ago
- 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…☆12Updated 2 months ago
- Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models☆52Updated last month
- MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering. A comprehensive evaluation of multimodal large model multilingua…☆56Updated last month
- GLM Series Edge Models☆137Updated 2 months ago
- Here is a demo for PDF parser (Including OCR, object detection tools)☆34Updated 6 months ago
- Vary-tiny codebase upon LAVIS （for training from scratch）and a PDF image-text pairs data (about 600k including English/Chinese)☆81Updated 7 months ago