X1r0z

X1r0z's activity

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

updated a model 5 days ago

X1r0z/test-model

Updated 5 days ago • 19

published a model 5 days ago

X1r0z/test-model

Updated 5 days ago • 19

liked 3 datasets 7 months ago

PKU-Alignment/BeaverTails

Viewer • Updated Oct 17, 2023 • 364k • 11.7k • 90

Anthropic/hh-rlhf

Viewer • Updated May 26, 2023 • 169k • 21.6k • 1.65k

JailbreakV-28K/JailBreakV-28k

Viewer • Updated Jul 10, 2024 • 30.3k • 3.33k • 60

liked a Space 7 months ago

Sleeping

1

System Prompt Leakage Demo

🚰

1

Check system prompt leakage in LLM output

liked a dataset 7 months ago

gabrielchua/system-prompt-leakage

Viewer • Updated Nov 4, 2024 • 355k • 88 • 10

liked 5 datasets 9 months ago

walledai/WildJailbreak

Viewer • Updated Jul 31, 2024 • 2.21k • 125 • 4

qualifire/prompt-injections-benchmark

Viewer • Updated Feb 2, 2025 • 5k • 816 • 20

Mindgard/evaded-prompt-injection-and-jailbreak-samples

Viewer • Updated Apr 30, 2025 • 11.3k • 73 • 4

Aarushhh/awesome-prompts

Viewer • Updated Aug 31, 2024 • 9.92k • 2 • 3

Lakera/gandalf_ignore_instructions

Viewer • Updated Feb 28, 2025 • 1k • 317 • 33

liked a model 9 months ago

protectai/deberta-v3-base-prompt-injection-v2

Text Classification • 0.2B • Updated May 28, 2024 • 173k • • 84

liked 2 datasets 9 months ago

walledai/StrongREJECT

Viewer • Updated Oct 18, 2024 • 313 • 2.69k • 17

walledai/AdvBench

Viewer • Updated Jul 4, 2024 • 520 • 5.77k • 74

liked a Space 10 months ago

Running

44

LLM Guard Playground

🏢

44

Display interactive data apps

liked 3 models 10 months ago

meta-llama/Prompt-Guard-86M

Text Classification • 0.3B • Updated Nov 12, 2025 • 17k • • 300

meta-llama/Llama-Guard-3-8B

Text Generation • 8B • Updated Oct 11, 2024 • 35.4k • • 262

meta-llama/Llama-Guard-3-1B

Text Generation • 1B • Updated Sep 26, 2024 • 16.8k • 98

liked a Space 10 months ago

Running

320

LLM Embeddings Explained: A Visual and Intuitive Guide

🚀

320

How Language Models Turn Text into Meaning, From Traditional