Seth
sethupavan12
AI Engineer. Previously at @Microsoft
Languages
Loading contributions...
Top Repositories
Convert documents, images to high-quality Markdown using Vision LLMs. Built for RAG ingestion pipelines.
Bring back some of the greatest minds from the past and "whatsapp" with them
A really smart wallet that can do lot of useful onchain operations to help web3 newbies
A collection of awesome readme templates to display on your profile
Visualizations of the connections between chaos theory and fractals through the logistic map; made for Veritasium YouTube video
Repositories
66No description provided.
No description provided.
Convert documents, images to high-quality Markdown using Vision LLMs. Built for RAG ingestion pipelines.
OPVTON is the GAN model I trained that takes a clothing item, a human body and generates an image with the clothing item on the human even when there's occlusion in the torso area. It beats other SOTA models at the time of its creation.
A collection of awesome readme templates to display on your profile
Bring back some of the greatest minds from the past and "whatsapp" with them
No description provided.
An implementation of iterative deep research using the OpenAI Agents SDK
Visualizations of the connections between chaos theory and fractals through the logistic map; made for Veritasium YouTube video
Cryptopia is an all-in-one consumer wallet AI agent designed to revolutionise your digital asset experience. By integrating advanced blockchain analytics, real-time market data, and smart contract functionalities, Cryptopia serves as your comprehensive command centre for managing, analysing, and growing your crypto portfolio.
A really smart wallet that can do lot of useful onchain operations to help web3 newbies
Every AI Agent deserves a wallet.
Content for sysinternals.com
No description provided.
No description provided.
GraphRAG Server
A web-based tool for visualizing and exploring artifacts from Microsoft's GraphRAG.
A modular graph-based Retrieval-Augmented Generation (RAG) system for code.
A high-throughput and memory-efficient inference and serving engine for LLMs
Currently building a fun version of LMSYS for SLMs to evaluate "humanlikeness" of a model
Backend for human storage hackathon project. Submitted to ETH Global London 2024. Won runner's up prize in Filecoin category.
A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap
A alternative to Github Copilot for vscode until you get the access to github copilot
Get up and running with Llama 2 and other large language models locally
Reference implementation of Mistral AI 7B v0.1 model.
No description provided.
No description provided.
Let us control diffusion models!
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
No description provided.