Cyrus Nikolaidis

cynikolai's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in meta-llama/Prompt-Guard-86M about 1 month ago

How to detect words?

1

#17 opened about 1 month ago by GoominDev

liked a model about 2 months ago

facebook/hubert-base-ls960

Feature Extraction • Updated Nov 5, 2021 • 97k • 48

authored 2 papers about 2 months ago

The Llama 3 Herd of Models

Paper • 2407.21783 • Published Jul 31 • 107

CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Paper • 2408.01605 • Published Aug 2 • 1

New activity in meta-llama/Prompt-Guard-86M 3 months ago

Model classifies everything as unsafe

15

#15 opened 4 months ago by wagnew3

New activity in meta-llama/Prompt-Guard-86M 4 months ago

Open Sourcing Dataset?

2

#16 opened 4 months ago by johnnydevriese

Model is extremely sensitive to the word "ignore"

4

#14 opened 4 months ago by mstachow

upvoted a collection 4 months ago

Llama 3.1

Collection

This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated Sep 25 • 627

liked a Space 6 months ago

Running

54

📈

CyberSecEvalTest

upvoted an article 6 months ago

view article

Article

CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models

May 24

• 21

upvoted a paper 11 months ago

Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Paper • 2312.04724 • Published Dec 7, 2023 • 20

authored a paper 12 months ago

Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Paper • 2312.04724 • Published Dec 7, 2023 • 20