Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.

real time face swap and one-click video deepfake with only a single image

A companion app for the Deluge by Synthstrom Audible

EuroPi: A reprogrammable Eurorack module based on the Raspberry Pi Pico

A simple digital synthesizer made in pure data in 2016

Active Record, Django-like queries, nested eager load and beauty __repr__ for SQLAlchemy

Grok open release

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

An unnecessarily tiny implementation of GPT-2 in NumPy.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

A fast, local neural text to speech system

Open-source Android/Desktop remake of Civ V

A curated list of engineering-related video games rated Very Positive or higher on Steam

Boids. they fly. they steer

[CC BY-NC-SA] A compendium of the community knowledge on game design and development

A simple tool to generate random ideas for mini-games

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

Go ahead and axolotl questions

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

a comprehensive collection of video game tech analysis resources

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

the statistics handbook open source repository

Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts

A guidance language for controlling large language models.