strongreject-15k-v1 is a parameter-efficient fine-tuned (PEFT) adapter for the google/gemma-2b model. It was trained on a 15k dataset to strengthen the model's ability to reject prompts that request harmful, unethical, or dangerous content. The model is hosted on Hugging Face and can be used with the Transformers library for local or cloud inference. It is fully open source with weights available for download and further fine-tuning.
Strongreject 15k sits in PulseGate's Other AI category. It focuses on fine-tuning language models to better reject unsafe or harmful user requests. Strongreject 15k is an open-source project aimed at AI researchers and developers. The project is open source (Open Source). Strongreject 15k is available on the web and API.
Behind Strongreject 15k is qylu4156, and it first shipped in 2024. Among its 3 catalogued features are PEFT adapter, harmful prompt rejection, and gemma base model.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match