A high-throughput and memory-efficient inference and serving engine for LLMs

Efficient Triton Kernels for LLM Training

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

A Gradio component that can be used to annotate images with bounding boxes.

UniTable: Towards a Unified Table Foundation Model

Examples in the MLX framework

A static blog build on top of Notion and NextJS, deployed on Vercel.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Train transformer language models with reinforcement learning.

An open source data labeling UI for LLM.

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.

Awesome deals on Black Friday: Apps, SaaS, Books, Courses, etc.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.

Extend existing LLMs way beyond the original training length with constant memory usage, and without retraining

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

A tiny little diffusion drawing app

FaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.

A tiny little diffusion drawing app.