Official repo for paper "MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions"

[EMNLP 2023] Official implementation of the algorithm ETSC: Exact Toeplitz-to-SSM Conversion our EMNLP 2023 paper - Accelerating Toeplitz Neural Network with Constant-time Inference Complexity

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作

Making large AI models cheaper, faster and more accessible

Locally run an Instruction-Tuned Chat-Style LLM

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。

Port of OpenAI's Whisper model in C/C++

Instruct-tune LLaMA on consumer hardware

The road to hack SysML and become an system expert

LLM inference in C/C++

stable diffusion webui colab

LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

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

📖 爬取 Stackoverflow 100万 条问答并简单分析

Quick Start LLaMA models with multiple methods, and fine-tune 7B/65B with One-Click.

AI绘画资料合集（包含国内外可使用平台、使用教程、参数教程、部署教程、业界新闻等等） Stable diffusion、AnimateDiff、Stable Cascade 、Stable SDXL Turbo

A professional cross-platform SSH/Sftp/Shell/Telnet/Serial terminal.

AI search & chat for all of Paul Graham’s essays.

A collection of libraries to optimise AI model performances

Inference code for Llama models

Easily compute clip embeddings and build a clip retrieval system with them

Easily compute clip embeddings and build a clip retrieval system with them

Rust 杂志 2022 （已终止）

Symphony Generation with Permutation Invariant Language Model

High performance container overlay networks on Linux. Enabling RDMA (on both InfiniBand and RoCE) and accelerating TCP to bare metal performance. Freeflow requires zero modification on application …

Kubernetes multi-cluster management and publishing platform

The easiest way to serve AI/ML models in production - Build Model Inference Service, LLM APIs, Multi-model Inference Graph/Pipelines, LLM/RAG apps, and more!

FinRL: Financial Reinforcement Learning. 🔥