VSCode AI coding assistant powered by self-hosted llama.cpp endpoint.

Tutorials on tinygrad

some books and papers and stuff

could we make an ml stack in 100,000 lines of code?

Parameter inference of music synthesizers to simplify sound design process. Supports Vital.

Source code for "FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control"

A Digital Twin System of Chess Playing (SRTP)

toolkit for interactive exhibitions

Machine Learning with Synthesizers

Save or export your private and public Slack messages, threads, files, and users locally without admin privileges.

An implementation of and AI for the game of Tak

Vehicular traffic flow simulator in road network, written in pure Python

Draw more samples

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capa…

Instrument any LLM to do actual stuff.

Distributed LLM inference for mobile, desktop and server.

Decoder only transformer, built from scratch with PyTorch

LLM101n: Let's build a Storyteller

lc0docker: run lc0 chess client and lichess bot under Docker and Kubernetes

Indexing Discord Help Channel Questions into Google

Implementation for MatMul-free LM.

Codebase for reproducing the experiments of the semantic uncertainty paper (paragraph-length experiments).

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.

datasets from the paper "Towards Understanding Sycophancy in Language Models"

32K I2C Smart Serial EEPROM