albertwujj
Follow
Stars
A Telegram bot for voice-to-voice conversations with AI built with Vocode
🤖 Build voice-based LLM agents. Modular + open source.
Mini DL Library with eager automatic differentiation. Supports backpropagation over a dynamically built graph.
Concise, modular implementation of Multi-Scale Convolutional Recurrent Encoder Decoder: https://arxiv.org/abs/1811.08055
A Slay the Spire mod that allows a calling library to execute commands and optionally execute commands very quickly for use in AI projects
A Slay the Spire mod that allows players and coders to save and load state
A vault for securely storing and accessing AWS credentials in development environments
Small tool to convert an IAM Policy in JSON format into a Terraform aws_iam_policy_document
Simple text-based game
A simple puzzle game, https://www.wuthejeff.com/send-a-damned-message/
An open source productivity tool drawing inspiration from workflowy and vim
ext2 File System in C, from inodes to terminal commands, with WSU's KC Wang’s textbook
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Spriteworld: a flexible, configurable python-based reinforcement learning environment
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
albertwujj / gpt-2
Forked from openai/gpt-2Increased the efficiency of GPT-2 by one pass/token per prompt. See https://github.com/openai/gpt-2/pull/119. Code for the paper "Language Models are Unsupervised Multitask Learners"
🎓 Path to a free self-taught education in Computer Science!
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Java and Arduino communication to control and process a blast furnace monitoring system.