LLM based data scientist, AI native data application.

本项目旨在分享大模型相关技术原理以及实战经验。

Gorilla: An API store for LLMs

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

Focus on prompting and generating

Fay是一个完整的开源项目，包含Fay控制器及数字人模型，可灵活组合出不同的应用场景：虚拟主播、现场推销货、商品导购、语音助理、远程语音助理、数字人互动、数字人面试官及心理测评、贾维斯、Her。 开源项目，非产品试用！！！

Easy to use open source fast database for search | Good alternative to Elasticsearch now | Drop-in replacement for E in the ELK soon

Question Answering with Custom FIles using LLMs

LakeSoul is an end-to-end, realtime and cloud native Lakehouse framework with fast data ingestion, concurrent update and incremental data analytics on cloud storages for both BI and AI applications.

🌟 The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

中文医疗对话模型扁鹊(BianQue)

🧙 The modern replacement for Airflow. Build, run, and manage data pipelines for integrating and transforming data.

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

A unified end-to-end machine intelligence platform

the AI-native open-source embedding database

Stable Diffusion web UI

骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技

A high-performance observability data pipeline.

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

云原生一站式机器学习平台，多租户，数据资产，notebook在线开发，拖拉拽任务流编排，多机多卡分布式训练，超参搜索，推理服务，多集群调度，多项目组资源组，边缘计算，大模型实时训练, ai应用商店

总结Prompt&LLM论文，开源数据&模型，AIGC应用

langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识的 ChatGLM 问答

An open-source tool-augmented conversational language model from Fudan University

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All.

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

The Modern Data Stack 🐰 — Directus is an instant REST+GraphQL API and intuitive no-code data collaboration app for any SQL database.

Sample Data Lakehouse deployed in Docker containers using Apache Iceberg, Minio, Trino and a Hive Metastore. Can be used for local testing.

Code and documentation to train Stanford's Alpaca models, and generate the data.