Stars
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
The official Python SDK for Model Context Protocol servers and clients
Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.
No fortress, purely open ground. OpenManus is Coming.
Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.
Integrate the DeepSeek API into popular softwares
C++实现的跨平台数独游戏，命令行操作易上手，可以在开发间隙用来放松身心。数百行代码，初学者也可以轻松掌握。
[ICML 2025] SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & RFT & Dynamic Sampling & Async Agent RL)
The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。
This is a user guide for the MiniCPM and MiniCPM-V series of small language models (SLMs) developed by ModelBest. “面壁小钢炮” focuses on achieving exceptional performance on the edge.
a comfyui node for automatic generate image label for running lora or dreambooth training on flux series models
小红书（XiaoHongShu、RedNote）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
Implementation of SegFormer in PyTorch
Evaluation code and datasets for the ACL 2024 paper, VISTA: Visualized Text Embedding for Universal Multi-Modal Retrieval. The original code and model can be accessed at FlagEmbedding.
Simple implementation of OpenAI CLIP model in PyTorch.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
Notebooks using the Hugging Face libraries 🤗
Witness the aha moment of VLM with less than $3.
GIT: A Generative Image-to-text Transformer for Vision and Language
Fully open reproduction of DeepSeek-R1