#
VJaGG
Follow
Starred repositories
Reference implementation for DPO (Direct Preference Optimization)
Official implementation of ID-unaware Deepfake Detection Model
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
Scripts for fine-tuning Llama2 via SFT and DPO.
本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/
Pytorch implementation of F3Net (ECCV 2020 F3Net: Frequency in Face Forgery Network)
A comprehensive benchmark of deepfake detection
A prize winning solution for DFDC challenge
Approaching (Almost) Any Machine Learning Problem
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。
《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).
Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
pytorch implement of Lookahead Optimizer
Python best practices guidebook, written for humans.
Python最佳实践指南。 The chinese translation of "Hitchhiker's Guide to Python".
[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model…
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion
Custom nodes for SDXL and SD1.5 including Multi-ControlNet, LoRA, Aspect Ratio, Process Switches, and many more nodes.