Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Data validation using Python type hints

Official codes of ICCV2023 paper: <<FemtoDet: an object detection baseline for energy versus performance tradeoffs>>

Openpose Editor for AUTOMATIC1111's stable-diffusion-webui

Nightly release of ControlNet 1.1

A Gradio web UI for Large Language Models with support for multiple inference backends.

OpenAGI: When LLM Meets Domain Experts

A data visualization and analytics component, especially well-suited for large and/or streaming datasets.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

NeRFshop: Interactive Editing of Neural Radiance Fields

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

Source code for Twitter's Recommendation Algorithm

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

SageMaker Studio Labの教材を紹介するリポジトリ。

Using Low-rank adaptation to quickly fine-tune diffusion models.

Stable Diffusion web UI

Depth map library for use with the Control Net extension for Automatic1111/stable-diffusion-webui

Enables use of ChatGPT directly from the UI

AudioLDM: Generate speech, sound effects, music and beyond, with text.

A web-based collaborative LaTeX editor

A set of scikit-learn style transformers for Polars

WebUI extension for using Blip2

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

Inference code for Llama models

Making large AI models cheaper, faster and more accessible