Collection of AWESOME vision-language models for vision tasks

多模态 MM +Chat 合集

iBOT 🤖: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

OLMoE: Open Mixture-of-Experts Language Models

Code for our paper "Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers"

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

4M: Massively Multimodal Masked Modeling

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

PyTorch code and models for the DINOv2 self-supervised learning method.

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

llama3 implementation one matrix multiplication at a time

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

A fast MoE impl for PyTorch

Official repository for "AM-RADIO: Reduce All Domains Into One"

🌍 Discover our global repository of countries, states, and cities! 🏙️ Get comprehensive data in JSON, SQL, PSQL, XML, YAML, and CSV formats. Access ISO2, ISO3 codes, country code, capital, native l…

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

[CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"

The official Meta Llama 3 GitHub site

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

(ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life