LocalAlign_llama3.1_8B
yuyangGong · Kit
A LoRA adapter for Llama-3.1-8B-Instruct that trains it to follow trusted instructions and ignore commands hidden in external data. A prompt injection defense…
New
AI projects from Hugging Face
Categories and filters
Listings
Qwen3-4B P9 Honeypot
samliumay · Kit
A small research adapter for Qwen3-4B that turns the model into a decoy. It sends a silent alert to a local collector when it spots an attack on its secrets, t…
New
deberta-v3-base-prompt-injection-v2
protectai · Kit
Flags English text that tries to hijack a language model, labeling each input as benign or prompt injection. For developers who screen user input in LLM apps.
New