TongLi3701

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

ChatChat

Chat Chat, your own unified chat and search to AI platform, with a simple and easy to use interface.

Qwen-Agent

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

grok-1

Grok open release

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

InfLLM

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

milvus

A cloud-native vector database, storage for next generation AI applications

VideoGPT

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

danswer

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

ringattention

Transformers with Arbitrarily Large Context

LWM

video_captioning_datasets

Summary about Video-to-Text datasets. This repository is part of the review paper *Bridging Vision and Language from the Video-to-Text Perspective: A Comprehensive Review*

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

agents

An Open-source Framework for Autonomous Language Agents

Feishu-On-Leave-Status-Sync

This is a cron job which will periodically sync the on-leave status on Feishu.

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

QAnything

Question and Answer based on Anything.

nanotron

Minimalistic large language model 3D-parallelism training

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

Chinese-Mixtral-8x7B

中文Mixtral-8x7B（Chinese-Mixtral-8x7B）

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

Machine-Mindset

An MBTI Exploration of Large Language Models

modelscope-agent

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

SwiftInfer

Efficient AI Inference & Serving

YAYI-UIE

雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>