Martin Gubri's picture

8 3 8

Martin Gubri

mgubri

·

https://gubri.eu/

AI & ML interests

Adversarial Examples, Machine Learning, Information Security, Statistics

Recent Activity

upvoted a collection 2 days ago

new activity 6 days ago

parameterlab/apricot_clustering_coqa_deberta-v3-base_for_gpt-3.5-turbo-0125:Adding `safetensors` variant of this model

new activity 6 days ago

parameterlab/apricot_binary_coqa_deberta-v3-base_for_gpt-3.5-turbo-0125:Adding `safetensors` variant of this model

View all activity

Organizations

mgubri's activity

upvoted a collection 2 days ago

📚 Papers

List of research articles of Parameter Lab • 4 items • Updated 2 days ago • 1

upvoted a collection 30 days ago

Model with Circuit Breakers

SoTA models with circuit breakers inserted. Top safety performance without losing capabilities. • 3 items • Updated Oct 25, 2024 • 5

upvoted a collection 2 months ago

🍑 Apricot Models

Fine-tuned models for black-box LLM calibration, trained for "Apricot: Calibrating Large Language Models Using Their Generations Only" (ACL 2024) • 9 items • Updated Nov 20, 2024 • 3