NanoGPT (124M) in 3 minutes

Training Large Language Model to Reason in a Continuous Latent Space

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Rust project ideas for Google Summer of Code

🤗 Agents: the simplest building blocks to build and run LLM agents.

GSM-Symbolic templates and generated data

A course on aligning smol models.

Entropy Based Sampling and Parallel CoT Decoding

MLX port for xjdr's entropix sampler (mimics jax implementation)

PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture in…

Examples in the MLX framework

The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".

Inspect: A framework for large language model evaluations

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

A library for generative social simulation

This repository will contain the presentation and python jupyter notebooks for the DataHack Summit 2024 conference talk, Improving Real-world Retrieval Augmented Generation Systems, focusing on the…

High performance AI inference stack. Built for production. @ziglang / @openxla / MLIR / @bazelbuild

Solve Puzzles. Learn Metal 🤘

Code to reproduce key results for "Interpreting Attention Layer Outputs with Sparse Autoencoders"

A new markup-based typesetting system that is powerful and easy to learn.

This repository implements a simpleVAE for training on CPU on the MNIST dataset and provides ability to visualize the latent space, entire manifold as well as visualize how numbers interpolate betw…