Rummage-8B
It's Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total
With ablation where the harmless dataset was tatsu-labs/alpaca and the harmful dataset was hooking-dev/SexyGPT-ChatML.
- Downloads last month
- 56
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support