Fiona Pollack's starred repositories
algorithmic-efficiency
MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.
ai-and-efficiency
Submissions for AI and Efficiency SOTA's
nuclear_simulation
US-China Nuclear Confrontation Simulation
lm-evaluation-harness
A framework for few-shot evaluation of language models.
alpaca-lora
Instruct-tune LLaMA on consumer hardware
BLOOM-LORA
Due to restriction of LLaMA, we try to reimplement BLOOM-LoRA (much less restricted BLOOM license here https://huggingface.co/spaces/bigscience/license) using Alpaca-LoRA and Alpaca_data_cleaned.json
toy-models-of-superposition
Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
machine-learning-exams
This repository contains links to machine learning exams, homework assignments, and exercises that can help you test your understanding.
diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
Audio-Classification
Pytorch code for "Rethinking CNN Models for Audio Classification"
tuned-lens
Tools for understanding how transformer predictions are built layer-by-layer
TransformerLens
A library for mechanistic interpretability of GPT-style language models
squigglepy
Squiggle programming language for intuitive probabilistic estimation features in Python
toy_takeoff_modeling
quick and hacky but flexible takeoff speeds model
spectre-attack-sgx
Spectre attack against SGX enclave
code-generator
Generators for kube-like API types
SpaceX-API
:rocket: Open Source REST API for SpaceX launch, rocket, core, capsule, starlink, launchpad, and landing pad data.
gpt-3-experiments
Test prompts for OpenAI's GPT-3 API and the resulting AI-generated texts.