收集关于嵌入式领域的机器学习算法实现的进展、相关论文和文章、开发库等，帮助初学者快速了解、学习和入门嵌入式领域的机器学习。CC-BY-NC-SA 4.0。

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

MedicalGPT-zh：一个基于ChatGLM的在高质量指令数据集微调的中文医疗对话语言模型

A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.

LLM对话生成工具

DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financ…

从0开始，将chatgpt的技术路线跑一遍。

大模型基础: 一文了解大模型基础知识

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Making data higher-quality, juicier, and more digestible for foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

A simulation framework based on ROS2 and LLMs(like GPT) for robot interaction tasks in the era of large models

YOLOv8 Segmentation with DeepSORT Object Tracking (ID + Trails)

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

Combining "segment-anything" with MOT, it create the era of "MOTS"

MOTSFusion: Track to Reconstruct and Reconstruct to Track

Tools for evaluating and visualizing results for the Multi Object Tracking and Segmentation (MOTS) task

TrackR-CNN baseline method for Multi-Object Tracking and Segmentation (MOTS)

A well-designed tracker for multiple object tracking (MOT) in computer vision, further experiments are needed to examine the effectiveness of our proposed method.

[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

[CVPR2022] DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box