ほぼ完全にベース-30B
https://huggingface.co/ehartford/based-30b So, as I was working on Wizard-Vicuna-30b-Uncensored and WizardLM-Uncensored-Falcon-7b, I came to the realization that these models, despite being trained with no refusals, were still refusing. How could this be? It dawned on me, that the foundational model itself must have developed its own opinions through the course of their ingestion of large amounts…