The following is a light-weight classification model designed to score the NCII risk of image editing prompts. General-purpose image-editing models have recently become more performant, particularly in their ability to preserve the identity of individual people while making photo-realistic changes to a picture. This has led to increased concerns about abuse of models to create **non-consensual intimate imagery (NCII)** from ordinary photos. As a result, some jurisdictions, including the EU, are introducing regulation mandating deployers to add targeted guardrails to prevent users from easily nudifying subjects of photographs or editing images to sexualize them without their consent. This model acts as a small **prompt guard**: it scores whether an instruction looks like an edit request that has a high risk of enabling NCII creation.
A fast, multilingual classifier that flags **prompt injection and jailbreak attempts**, both in **user messages** (direct) and in **untrusted content an AI agent reads**: emails, web pages, documents, RAG chunks, and tool/API outputs (indirect). Labels: `SAFE` (0) and `INJECTION` (1). This is the same convention as `protectai/deberta-v3-base-prompt-injection-v2`, so the model is a drop-in replacement in code and tools built for that one. `INJECTION` means the text tries to **change what the AI reading it does**, against the instructions of its developer or user:
This is a classifier for judging the educational value of web pages. It was developed to filter and curate educational content from web datasets and was trained on 450k annotations generated by LLama3-70B-instruct for web samples from FineWeb dataset. We used this classifier to build FineWeb-Edu dataset. To load the FineWeb-Edu classifier, use the following code: The classifier was trained on 450,000 pairs of web samples and their scores from 0 to 5, generated by Llama3. The samples were annotated based on their educational quality with 0 being not educational and 5 being highly educational.
