LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report

1 code implementation • 29 Apr 2024 • Justin Zhao, Timothy Wang, Wael Abid, Geoffrey Angus, Arnav Garg, Jeffery Kinnison, Alex Sherstinsky, Piero Molino, Travis Addair, Devvret Rishi

LoRAX powers LoRA Land, a web application that hosts 25 LoRA fine-tuned Mistral-7B LLMs on a single NVIDIA A100 GPU with 80GB memory.

HomOpt: A Homotopy-Based Hyperparameter Optimization Method

1 code implementation • 7 Aug 2023 • Sophia J. Abraham, Kehelwala D. G. Maduranga, Jeffery Kinnison, Zachariah Carmichael, Jonathan D. Hauenstein, Walter J. Scheirer

Traditional methods, like grid search and Bayesian optimization, often struggle to quickly adapt and efficiently search the loss landscape.

Bayesian Optimization Hyperparameter Optimization +2

Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation

1 code implementation • WS 2019 • Kenton Murray, Jeffery Kinnison, Toan Q. Nguyen, Walter Scheirer, David Chiang

Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation.

Machine Translation Translation

Learning-Free Iris Segmentation Revisited: A First Step Toward Fast Volumetric Operation Over Video Samples

1 code implementation • 6 Jan 2019 • Jeffery Kinnison, Mateusz Trokielewicz, Camila Carballo, Adam Czajka, Walter Scheirer

Subject matching performance in iris biometrics is contingent upon fast, high-quality iris segmentation.

Iris Segmentation Segmentation

A Neurobiological Evaluation Metric for Neural Network Model Search

1 code implementation • CVPR 2019 • Nathaniel Blanchard, Jeffery Kinnison, Brandon RichardWebster, Pouya Bashivan, Walter J. Scheirer

In this paper we introduce a human-model similarity (HMS) metric, which quantifies the similarity of human fMRI and network activation behavior.