LLM101n: Let's build a Storyteller

SCAMPS Dataset

Toolkit for attaching, training, saving and loading of new heads for transformer models

🖼️ Create beautiful maps from OpenStreetMap data in a streamlit webapp

[DEPRECATED] Workshop material to teach Rust in the style of Railsbridge

Master programming by recreating your favorite technologies from scratch.

Minimalistic large language model 3D-parallelism training

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Code for the paper "Evaluating Large Language Models Trained on Code"

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

Let us control diffusion models!

WebUI extension for ControlNet

A quick guide (especially) for trending instruction finetuning datasets

The MATH Dataset (NeurIPS 2021)

Улучшеный Minecraft лаунчер на основе sashok's742 v3

Serve, optimize and scale PyTorch models in production

Code Repository for Liquid Time-Constant Networks (LTCs)

My publications on Medium

Efficient few-shot learning with Sentence Transformers

code for Data Science From Scratch book

A multi-voice TTS system trained with an emphasis on quality

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

Streamlit — A faster way to build and share data apps.

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

A library (and demo applications) for face- and facial feature detection and real-time tracking in 2d-images