AI模型聚合管理中转分发系统，一个应用管理您的所有AI模型，支持将多种大模型转为统一格式调用，支持OpenAI、Claude、Gemini等格式，可供个人或者企业内部管理与分发渠道使用。🍥 The next-generation LLM gateway and AI asset management system supports multiple languages.

Fast, Flexible and Portable Structured Generation

AI Observability & Evaluation

Structured Outputs

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Perceptual video quality assessment based on multi-method fusion.

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

Differentiable Vector Graphics Rasterization

Rembg is a tool to remove images background

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Raster to Vector Graphics Converter

LAVIS - A One-stop Library for Language-Vision Intelligence

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

PyTorch code to run synthetic experiments.

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

PyTorch package for the discrete VAE used for DALL·E.

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

Convex potential flows

Optimization with orthogonal constraints and on general manifolds

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

code for "Residual Flows for Invertible Generative Modeling".

Make huge neural nets fit in memory

code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

Probabilistic reasoning and statistical analysis in TensorFlow

A probabilistic programming language in TensorFlow. Deep generative models, variational inference.