yoonholee

Triton-Puzzles

Puzzles for learning Triton

kronfluence

Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature

spring2024-lectures

intrinsic_fewshot_hardness

This is the github repo for EMNLP 2022 paper "On Measuring the Intrinsic Few-Shot Hardness of Datasets".

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

NPHardEval

Repository for NPHardEval, a quantified-dynamic benchmark of LLMs

auto-ft

discovering_latent_knowledge

ml-engineering

Machine Learning Engineering Open Book

knowyourdata

A tool to help researchers and product teams understand datasets with the goal of improving data quality, and mitigating fairness and bias issues.

DescribeDistributionalDifferences

Code for preprint: Summarizing Differences between Text Distributions with Natural Language

clip-retrieval

Easily compute clip embeddings and build a clip retrieval system with them

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

cursor

The AI-powered code editor

PUG

This is the repository for the Photorealistic Unreal Graphics (PUG) datasets for representation learning.

b2t

Bias-to-Text: Debiasing Unknown Visual Biases through Language Interpretation

dcm

Codebase for "Conservative Prediction via Data-Driven Confidence Minimization"

surgical-finetuning

Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023

afr

AFR code

DataDistributionTransferLearning

Sophia

The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

CloserLookAgainFewShot

[ICML 2023] A Closer Look at Few-shot Classification Again

llm-numbers

Numbers every LLM developer should know

StableLM

StableLM: Stability AI Language Models

imagenet-testbed

ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."

scaling-laws-openclip

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

free-lunch

Implementation of experiments from The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

grokking-squared

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.