A latent text-to-image diffusion model

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The fastai deep learning library

🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained

Python programs, usually short, of considerable difficulty, to perfect particular skills.

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

A High-Quality Real Time Upscaler for Anime Video

Data and code behind the articles and graphics at FiveThirtyEight

llama3 implementation one matrix multiplication at a time

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Image restoration with neural networks but without learning.

A collection of pre-trained, state-of-the-art models in the ONNX format

Using Low-rank adaptation to quickly fine-tune diffusion models.

Simple tutorials using Google's TensorFlow Framework

From the basics to slightly more interesting applications of Tensorflow

fast.ai Courses

Taming Transformers for High-Resolution Image Synthesis

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

A better notebook for Scala (and more)

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.

Tutorials for creating and using ONNX models

Kandinsky 2 — multilingual text2image latent diffusion model

Simple UI for LLM Model Finetuning

Deep Reinforcement Learning: Zero to Hero!

Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes

This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) avai…