Foundational model for the Neurosity Crown

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

Example models using DeepSpeed

LLM101n: Let's build a Storyteller

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Cutting edge AI technology for automated audio transcription. A nice GUI for OpenAIs Whisper and pyannote (speaker identification)

A playbook for systematically maximizing the performance of deep learning models.

A minimal GPU design in Verilog to learn how GPUs work from the ground up

lightweight, standalone C++ inference engine for Google's Gemma models.

The official Meta Llama 3 GitHub site

Improving transcription performance of OpenAI Whisper for CPU based deployment

LLM training in simple, raw C/CUDA

🙌 OpenHands: AI-Driven Development

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Fast bare-bones BPE for modern tokenizer training

The official PyTorch implementation of Google's Gemma models

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

🔥 Machine Learning Notebooks

Learning the Variant Call Format

An rclone script to perform backups

Helper scripts for biological data processing from Sentieon