Investigating attention masks learned from other tasks repurposed for cloud masking

Training Sparse Autoencoders on Language Models

A 100x faster SVD for PyTorch⚡️

NanoGPT (124M) quality in 7.8 8xH100-minutes

This is the repository for the distill web framework

RWKV centralised docs for the community

Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI

Examples of how the GalaxiesML dataset can be used

A port of DOOM for a quantum computer

Implementation of the Prithvi WxC Foundation Model and Downstream Tasks

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Expandable Datasets for Earth Observation

Python routines for Machine Learning applications for Earth Observation

Implemenation of PQMass from Lemos et al. 2024

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

nanoGPT style version of Llama 3.1

PyTorch implementation of models from the Zamba2 series.

Code for Leung, Bovy & Speagle 2024

Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and representation of player Elo.

The Multilayer Perceptron Language Model

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

A codebase dedicated to exploring multimodal learning approaches by integrating images of host galaxies of supernovae and their corresponding light-curves and spectra.

[NeurIPS 2024] GenRL: Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state …

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Video code lecture on building nanoGPT from scratch

Fine-tune a 7B LLM on cosmology datasets