-
protectai/deberta-v3-base-prompt-injection-v2
Text Classification • 0.2B • Updated • 191k • • 84 -
openai/gpt-oss-safeguard-20b
Text Generation • 22B • Updated • 10.5k • • 180 -
meta-llama/Llama-Prompt-Guard-2-86M
Text Classification • 0.3B • Updated • 22.3k • • 77 -
leolee99/PIGuard
Text Classification • 0.2B • Updated • 1.8k • 4
Lipeng (Tony) He
ttttonyhe
·
AI & ML interests
Trustworthy Machine Learning
Recent Activity
authored
a paper
14 days ago
Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
submitted
a paper
15 days ago
Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
updated
a collection
16 days ago
Red-Teaming Models & Datasets
Organizations
Open Embedding Models
-
Running on CPU Upgrade6.96k
MTEB Leaderboard
🥇6.96kEmbedding Leaderboard
-
Qwen/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 1.88M • • 839 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 674k • • 1.42k -
nomic-ai/nomic-embed-text-v2-moe
Sentence Similarity • 0.5B • Updated • 906k • 449
Red-Teaming Models & Datasets
Novel Models
Guardrails
-
protectai/deberta-v3-base-prompt-injection-v2
Text Classification • 0.2B • Updated • 191k • • 84 -
openai/gpt-oss-safeguard-20b
Text Generation • 22B • Updated • 10.5k • • 180 -
meta-llama/Llama-Prompt-Guard-2-86M
Text Classification • 0.3B • Updated • 22.3k • • 77 -
leolee99/PIGuard
Text Classification • 0.2B • Updated • 1.8k • 4
Specialized LLMs
Open Embedding Models
-
Running on CPU Upgrade6.96k
MTEB Leaderboard
🥇6.96kEmbedding Leaderboard
-
Qwen/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 1.88M • • 839 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 674k • • 1.42k -
nomic-ai/nomic-embed-text-v2-moe
Sentence Similarity • 0.5B • Updated • 906k • 449
Domain-specific Datasets
Red-Teaming Models & Datasets
SOTA Medium-sized Models
Novel Models
Templates