cydiachen

gpt4free

The official gpt4free repository | various collection of powerful language models

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

MNBVC

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

wechatDownload

微信公众号文章批量下载工具，支持图片、评论下载，支持保存html/md/pdf/docx文件

Qwen-Agent

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

MetaTransformer

Meta-Transformer for Unified Multimodal Learning

word-to-markdown

A ruby gem to liberate content from Microsoft Word documents

fastmoe

A fast MoE impl for PyTorch

LLaVA-pp

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

Chat-UniVi

[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

poe-api-wrapper

👾 A Python API wrapper for Poe.com. With this, you will have free access to ChatGPT, Claude, Llama, Gemini, Google-PaLM and more! 🚀

Groma

Grounded Multimodal Large Language Model with Localized Visual Tokenization

opennsfw2

Keras implementation of the Yahoo Open-NSFW model

ArXivQA

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

VCoder

VCoder: Versatile Vision Encoders for Multimodal Large Language Models, arXiv 2023 / CVPR 2024

rknn-llm

protest-detection-violence-estimation

Implementation of the model used in the paper Protest Activity Detection and Perceived Violence Estimation from Social Media Images (ACM Multimedia 2017)

AesBench

An expert benchmark aiming to comprehensively evaluate the aesthetic perception capacities of MLLMs.

BAdam

InsTag

InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning

InstructDoc

InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)

MuLan

MuLan: Adapting Multilingual Diffusion Models for 110+ Languages (无需额外训练为任意扩散模型支持多语言能力)

LLaVA-Hound-DPO

ExplainableVQA

[ACMMM Oral, 2023] "Towards Explainable In-the-wild Video Quality Assessment: A Database and a Language-Prompted Approach"

MLLM-protector

The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"

msccl-executor-nccl

llm-vision-datasets

Collection of image and video datasets for generative AI and multimodal visual AI

MSWord_ChatGPT

How to use ChatGPT in MS Word

matrix

a crawler base on scrapy, for crawl taboo items

ReAlign

Reformatted Alignment