Minos Refusal Classifier - Detect Refusals in Text - Install and Test Locally
AI Summary
In this video, Fad Miraa introduces Minos, a lightweight classifier model developed by Nouse Research for detecting refusals in text. Minos acts as a guardrail in inference pipelines by ensuring that responses from a language model (LLM) do not contain unwanted content. The model is based on a modern BERT architecture and excels at identifying refusals in question-response pairs. The video includes a guide on installing Minos using Ubuntu and demonstrates how the model works with different example queries, showing its effectiveness in classifying responses as either refusals or non-refusals. The video also highlights the historical significance behind the name ‘Minos’ and discusses the potential applications of the classifier in various scenarios. Users are encouraged to explore this model and share their thoughts.
Description
This video locally installs Nous Research Minos, a lightweight classifier designed to detect refusals in text.
🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon:
https://bit.ly/fahd-mirza
Coupon code: FahdMirza
🚀 This video is sponsored by https://camel-ai.org/ which is an open-source community focused on building multi-agent infrastructures.
🔥 Buy Me a Coffee to support the channel: https://ko-fi.com/fahdmirza
▶ Become a Patron 🔥 - https://patreon.com/FahdMirza
PLEASE FOLLOW ME:
▶ LinkedIn: https://www.linkedin.com/in/fahdmirza/
▶ YouTube: https://www.youtube.com/@fahdmirza
▶ Blog: https://www.fahdmirza.com
RELATED VIDEOS:
▶ Resource https://huggingface.co/NousResearch/Minos-v1
All rights reserved © Fahd Mirza