-
openai/gpt-oss-safeguard-20b
Text Generation • 22B • Updated • 20.7k • • 187 -
Qwen/Qwen3Guard-Stream-0.6B
Feature Extraction • 0.6B • Updated • 686 • 26 -
meta-llama/Llama-Guard-4-12B
Image-to-Text • 12B • Updated • 58.8k • 77 -
meta-llama/Llama-Prompt-Guard-2-86M
Text Classification • 0.3B • Updated • 16.1k • • 79
Lipeng (Tony) He
ttttonyhe
·
AI & ML interests
Trustworthy Machine Learning
Recent Activity
updated
a collection
1 day ago
LLM Guardrails
upvoted
an
article
1 day ago
Granite 4.0 Nano: Just how small can you go?
updated
a collection
1 day ago
Small Models
Organizations
Red-Teaming Models
Dense LLMs
Small Models
< 1GB
Domain-specific Datasets
Templates
Specialized LLMs
Red-Teaming Datasets
Reasoning LLMs
Embedding Models
-
Running on CPU Upgrade6.99k
MTEB Leaderboard
🥇6.99kEmbedding Leaderboard
-
Qwen/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 2.13M • • 859 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 814k • • 1.44k -
nomic-ai/nomic-embed-text-v2-moe
Sentence Similarity • 0.5B • Updated • 1.13M • 450
Novel Model Architectures
LLM Guardrails
-
openai/gpt-oss-safeguard-20b
Text Generation • 22B • Updated • 20.7k • • 187 -
Qwen/Qwen3Guard-Stream-0.6B
Feature Extraction • 0.6B • Updated • 686 • 26 -
meta-llama/Llama-Guard-4-12B
Image-to-Text • 12B • Updated • 58.8k • 77 -
meta-llama/Llama-Prompt-Guard-2-86M
Text Classification • 0.3B • Updated • 16.1k • • 79
Specialized LLMs
Red-Teaming Models
Red-Teaming Datasets
Dense LLMs
Reasoning LLMs
Small Models
< 1GB
Embedding Models
-
Running on CPU Upgrade6.99k
MTEB Leaderboard
🥇6.99kEmbedding Leaderboard
-
Qwen/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 2.13M • • 859 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 814k • • 1.44k -
nomic-ai/nomic-embed-text-v2-moe
Sentence Similarity • 0.5B • Updated • 1.13M • 450
Domain-specific Datasets
Novel Model Architectures
Templates