ShantanuNair

7bal091sc

ControlNet

Let us control diffusion models!

docker-diffusers-api

Diffusers / Stable Diffusion in docker with a REST API, supporting various models, pipelines & schedulers.

gpt_index

An index created by GPT to organize external information and answer queries!

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

serverless-template-flan-t5

Basic template for using Flan-t5 on Banana's serverless GPU platform. Ready for 1-Click deploy

Spoken-SQuAD

A spoken question answering dataset on SQUAD

stable-ts

Timestamping Spoken Words

supabase-py

Python Client for Supabase

targetedSummarization

TextReducer - A Tool for Summarization and Information Extraction

torchdynamo

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

websocketd

Turn any program that uses STDIN/STDOUT into a WebSocket server. Like inetd, but for WebSockets.

wespeaker

Production First and Production Ready Speaker Recognition Toolkit

whisper

whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

AgentGPT

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

audioscope

audio visualizers true to the sound

babyagi

chatgpt-retrieval-plugin

gpt-repository-loader

Convert code repos into an LLM prompt-friendly format. Mostly built by GPT-4.

guidance

A guidance language for controlling large language models.

langchain-aws-template

Application template for service api using langchain and generative model services

llama-dl

High-speed download of LLaMA, Facebook's 65B parameter GPT model

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

nextjs-langchain-example

Demo of using LangChain.js with Next.js and Vercel Edge Functions (to stream the response)

node-ytdl-core

YouTube video downloader in javascript.

RasaGPT

💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

underthebar

"Under the Bar" - a basic 3rd-party client application for Hevy (see hevyapp.com)

wav2lip-HD

Alternative to Flawless AI's TrueSync. Make lips in video match provided audio using the power of Wav2Lip and GFPGAN.