Universal cross-platform tokenizers binding to HF and sentencepiece

LPS22HB Library for Arduino

Structured information extraction with LLMs

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

API and library for MAVLink compatible systems written in C++17

MAVLink library for Rust.

Official reference C / C++ library for the v2 protocol

Visualizer for neural network, deep learning and machine learning models

Finetuning florence 2 on CATMuS.

Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"

[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/m…

cuDF - GPU DataFrame Library

SLAM navigation on simplified scenario (FastSLAM implementation using Python) based on Particle Filter (Sequential Monte Carlo). What happens when the visual support of a drone is missing?

This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)

[ICCV 2023] Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

OpenMMLab Computer Vision Foundation

[ICCV 2023] DETRs with Collaborative Hybrid Assignments Training

OpenMMLab Detection Toolbox and Benchmark

MoVA: Adapting Mixture of Vision Experts to Multimodal Context

Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object Detection"

The Abstraction and Reasoning Corpus

API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

Python toolkit for quantitative finance

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".