TencentARC / mllm-npu
mllm-npu: training multimodal large language models on Ascend NPUs
☆77Updated 3 weeks ago
Related projects: ⓘ
- 📖A small curated list of Awesome SD/DiT/ViT/Diffusion Inference with Distributed/Caching/Sampling: DistriFusion, PipeFusion, AsyncDiff, …☆64Updated 2 weeks ago
- ☆74Updated last week
- MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer☆189Updated 5 months ago
- MuLan: Adapting Multilingual Diffusion Models for 110+ Languages (无需额外训练为任意扩散模型支持多语言能力)☆124Updated 3 months ago
- Long Context Transfer from Language to Vision☆293Updated 3 weeks ago
- [ECCV 2024] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Mo…☆212Updated last month
- Please refer to our official repo at https://github.com/IVGSZ/Flash-VStream.☆48Updated last month
- Patch convolution to avoid large GPU memory usage of Conv2D☆73Updated 3 months ago
- ✨✨Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models☆128Updated last month
- A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.☆142Updated this week
- EVE: Encoder-Free Vision-Language Models☆207Updated 2 months ago
- 📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.☆134Updated last week
- [ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions☆112Updated 2 months ago
- OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text☆246Updated 3 weeks ago
- ☆100Updated last month
- 【ECCV2024】The official repo of Griffon series☆93Updated 2 months ago
- The official code of "RWKV-CLIP: A Robust Vision-Language Representation Learner"☆97Updated 2 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆34Updated 2 months ago
- This is the official implementation of the paper "Needle In A Multimodal Haystack"☆72Updated 2 months ago
- A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, qwen-vl, phi3-v …☆123Updated last week
- My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"☆168Updated last week
- This is the official implementation of "Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams"☆105Updated last month
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆36Updated 2 months ago
- ☆145Updated 2 months ago
- [ICCV2023] TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance☆60Updated 2 months ago
- MLLM-DataEngine: An Iterative Refinement Approach for MLLM☆34Updated 3 months ago
- ☆70Updated 6 months ago
- Harnessing 1.4M GPT4V-synthesized Data for A Lite Vision-Language Model☆239Updated 2 months ago
- minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora☆36Updated 5 months ago
- ☆168Updated 2 months ago