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

A latent text-to-image diffusion model

🔊 Text-Prompted Generative Audio Model

A curated list of insanely awesome libraries, packages and resources for Quants (Quantitative Finance)

A High-Quality Real Time Upscaler for Anime Video

StableLM: Stability AI Language Models

llama3 implementation one matrix multiplication at a time

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

High-Resolution Image Synthesis with Latent Diffusion Models

Jupyter Interactive Notebook

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

QLoRA: Efficient Finetuning of Quantized LLMs

Automatic extraction of relevant features from time series:

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

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K…

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

From the basics to slightly more interesting applications of Tensorflow

CoTracker is a model for tracking any point (pixel) on a video.

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

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

A python library for decision tree visualization and model interpretation.

A high performance implementation of HDBSCAN clustering.

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

Simple chat program that communicates using inaudible sounds

Structured state space sequence models

MARS5 speech model (TTS) from CAMB.AI

Easily compute clip embeddings and build a clip retrieval system with them