wenbohuang1002

minimind

「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！

zotfile

Zotero plugin to manage your attachments: automatically rename, move, and attach PDFs (or other files) to Zotero items, sync PDFs from your Zotero library to your (mobile) PDF reader (e.g. an iPad, Android tablet, etc.), and extract PDF annotations.

Paper-Writing-Tips

MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

Call-for-Reviewers

This project aims to collect the latest "call for reviewers" links from various top CS/ML/AI conferences/journals

unsloth

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Firefly

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

MediaCrawler

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

gkd

基于无障碍，高级选择器，订阅规则的自定义屏幕点击 Android 应用 | An Android APP with custom screen tapping based on Accessibility, Advanced Selectors, and Subscription Rules

CLoT

CVPR'24, Official Codebase of our Paper: "Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation".

XHS-Downloader

小红书链接提取/作品采集工具：提取账号发布、收藏、点赞、专辑作品链接；提取搜索结果作品、用户链接；采集小红书作品信息；提取小红书作品下载地址；下载小红书无水印作品文件！

VMamba

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

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

mamba

Mamba SSM architecture

iptv

Collection of publicly available IPTV channels from all over the world

Bilibili_UnFollow

由于小破站不提供批量取关的功能，因此自己做了一款哔哩哔哩（Bilibili）一键批量取关工具【b站、取关、取消关注、批量】

go-proxy-bingai

用 Vue3 和 Go 搭建的微软 New Bing 演示站点，拥有一致的 UI 体验，支持 ChatGPT 提示词，支持 API 调用，国内可用。

LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

texstudio

TeXstudio is a fully featured LaTeX editor. Our goal is to make writing LaTeX documents as easy and comfortable as possible.

ODConv

The official project website of "Omni-Dimensional Dynamic Convolution" (ODConv for short, spotlight in ICLR 2022).

ScConv

🕹️SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy

Oriented1D

Official code for ICCV 2023 paper "Convolutional Networks with Oriented 1D Kernels"

v2ray-core

A platform for building proxies to bypass network restrictions.

seu-cloud-study

prototypical-networks

Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

renet

[ICCV'21] Official PyTorch implementation of Relational Embedding for Few-Shot Classification

Embodied-One-Shot-Video-Recognition

The code of paper ACM Multimedia 2019: "Embodied One-Shot Video Recognition: Learning from Actions of a Virtual Embodied Agent"

AAAI2022_ContrastNet

code and data for AAAI2022 paper "ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification"

ContrastNet

rebiber

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

monodepth2

[ICCV 2019] Monocular depth estimation from a single image