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

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis

Implementation for MatMul-free LM.

Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

Official code for SwinFUSE to be presented in Self-supervised Modality-agnostic Pre-training Of Swin Transformers at ISBI'24

Implementations of recent research prototypes/demonstrations using MONAI.

A visual interface for understanding and interpreting Transformers

This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) avai…

llama3 implementation one matrix multiplication at a time

[T-PAMI] A curated list of self-supervised multimodal learning resources.

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

Official Repository for "DrEureka: Language Model Guided Sim-To-Real Transfer" (RSS 2024)

LLM inference in C/C++

Inference code for CodeLlama models

OpenUI let's you describe UI using your imagination, then see it rendered live.

Kolmogorov Arnold Networks

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

PyTorch implementation of Semi-supervised Vision Transformers

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

PyTorch code and models for V-JEPA self-supervised learning from video.

VMamba: Visual State Space Models，code is based on mamba

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation