Stars
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Scenic: A Jax Library for Computer Vision Research and Beyond
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
Python bindings for FFmpeg - with complex filtering support
linrongc / youtube-8m
Forked from google/youtube-8mCode of PhoenixLin(3rd place) in the 2nd Youtube8M Video Understanding Challenge
Llama中文社区,Llama3在线体验和微调模型已开放,实时汇总最新Llama3学习资料,已将所有代码更新适配Llama3,构建最好的中文Llama大模型,完全开源可商用
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Improved AnimateDiff for ComfyUI and Advanced Sampling Support
Enjoy the magic of Diffusion models!
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Open source Claude Artifacts – built with Llama 3.1 405B
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Wiseflow is an agile information mining tool that extracts concise messages from various sources such as websites, WeChat official accounts, social platforms, etc. It automatically categorizes and …
ACM MM 2021: 'Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection'
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
Docker汉化 Docker中文版 Docker汉化包 DockerDesktop汉化 Docker Windows Docker MAC
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调。
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
comfyui server to use comfyui API as easy as send a message
Code of "3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces"
A programming framework for agentic AI 🤖
DeepSeek Coder: Let the Code Write Itself
Pre-Training with Whole Word Masking for Chinese BERT(中文BERT-wwm系列模型)
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).