Tyler Vergho's Projects
A toolbox that provides hackable building blocks for generic 1D/2D/3D UNets, in PyTorch.
Automate debate evidence production with GPT-3.
Audio generation using diffusion models, in PyTorch.
A collection of audio autoencoders, in PyTorch.
Implementation of GANs and audio diffusion models.
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
Burn - A Flexible and Comprehensive Deep Learning Framework in Rust
Code for the paper: CNN-generated images are surprisingly easy to spot... for now https://peterwang512.github.io/CNNDetection/
A library for building excellent user experiences with Stacks.
Drills for Discrete Mathematics with Canvas Integration
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
RecTree app built in React Native.
Source code for the iPhone app High Frequency Tones. View on the App Store here: https://apps.apple.com/us/app/high-frequency-tones/id1511601653
Website for the Dartmouth Innovation, Development, and Entrepreneurship in Anesthesia (IDEA) Lab.
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
5th place submission to the 2023 NeurIPS LLM Efficiency Challenge.
Search platform for open-source debate evidence.
Create the building blocks of your app
Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch
Translate your drawings into music!
No clue how to respond – the website. Crowdsourced text message responses.
Check it out at http://nerdom.surge.sh/ (you'll have to wait for Heroku to wake up).