MonolithFoundation / BumblebeeLinks
A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.
☆38Updated last year
Alternatives and similar repositories for Bumblebee
Users that are interested in Bumblebee are comparing it to the libraries listed below
Sorting:
- Our 2nd-gen LMM☆34Updated last year
- ☆29Updated last year
- ☆57Updated last year
- ☆79Updated last year
- Chinese CLIP models with SOTA performance.☆58Updated 2 years ago
- 最简易的R1结果在小模型上的复现,阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证,对于强推理能力,think思考过程性内容是AGI/ASI的核心。☆44Updated 7 months ago
- Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models☆63Updated 11 months ago
- ☆181Updated 7 months ago
- Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.☆251Updated last month
- 基于baichuan-7b的开源多模态大语言模型☆72Updated last year
- ☆149Updated 2 weeks ago
- SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama: https://arxiv.org/abs/2408.09333v2☆126Updated 10 months ago
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆154Updated last year
- ☆27Updated 11 months ago
- ☆28Updated last year
- Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM☆101Updated last year
- [ICCV2025] A Token-level Text Image Foundation Model for Document Understanding☆121Updated last month
- Vary-tiny codebase upon LAVIS (for training from scratch)and a PDF image-text pairs data (about 600k including English/Chinese)☆86Updated last year
- SUS-Chat: Instruction tuning done right☆49Updated last year
- The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.☆255Updated this week
- GLM Series Edge Models☆149Updated 3 months ago
- Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines☆126Updated 10 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆41Updated last year
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆39Updated last year
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆57Updated 10 months ago
- ☆36Updated last year
- Multimodal Open-O1 (MO1) is designed to enhance the accuracy of inference models by utilizing a novel prompt-based approach. This tool wo…☆29Updated last year
- ☆17Updated last year
- Empirical Study Towards Building An Effective Multi-Modal Large Language Model☆22Updated 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…☆26Updated 7 months ago