Steve Gyutyan's repositories
reth-indexer
reth-indexer reads directly from the reth db and indexes the data into a postgres database with a simple config file and no extra setup.
streamlit-agent
Reference implementations of several LangChain agents as Streamlit apps
LMYield
Lightweight language for controlling OpenAI Chat API generations
pipeline-sec-filings
Preprocessing pipeline notebooks and API supporting text extraction from SEC documents
pytorch-memory-optim
This code repository contains the code used for my "Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorch" blog post.
lens-algorithm-playground
This app showcases various Lens recommendation algorithms and APIs available in the Lens ecosystem.
Replit-Container
Dockerized Replit-3B-Inference
glowby
Glowby Basic helps you create your own voice-based AI assistants with autonomous mode.
stable-diffusion-webui
Stable Diffusion web UI
UnityMLPySocket
UnityMLPySocket is an open-source project that demonstrates how to perform local machine learning (ML) inference with Unity using a Python socket server.
DragGAN
Official Code for DragGAN (SIGGRAPH 2023)
openai-agent
Connect NodeJS/Typescript Functions With OpenAI Function Call APIs!!
sd-webui-controlnet
WebUI extension for ControlNet
generative-disco
🎼 text-to-video system for music visualization
tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
ai-getting-started
A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs
lit-gpt
Implementation of Falcon, StableLM, Pythia, INCITE language models based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
studio
The studio is the main interface you'll use to build and edit your chatbot.
transformers.js
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
open_llama
OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
privateGPT
Interact privately with your documents using the power of GPT, 100% privately, no data leaks
llamaflow
The Typescript-first prompt engineering toolkit for working with chat based LLMs.
malleable-signatures
This repository implements a simplified PoC that demonstrates how signature malleability attacks using compact signatures can be executed.
localGPT
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.