ABRAMAR SOLUTION's picture

3

ABRAMAR SOLUTION

7rouz

·

AI & ML interests

None yet

Recent Activity

new activity about 4 hours ago

stefan-it/xlstm-german-wikipedia:SHAP values on this model

reacted to codelion's post with ❤️ 3 days ago

Perplexity released a dataset (BrowseSafe) and benchmark to catch and prevent malicious prompt-injection instructions in real-time. We trained a prompt injection classifier on BrowseSafe using adaptive-classifier with ModernBERT-base embeddings. 74.9% F1 on detecting prompt injection in web content. Model -> https://huggingface.co/adaptive-classifier/browsesafe Dataset -> https://huggingface.co/datasets/perplexity-ai/browsesafe-bench Repo -> https://github.com/codelion/adaptive-classifier

commented on a paper 6 days ago

Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

View all activity

Organizations

None yet

7rouz 's models

None public yet