AskVenice/venice-uncensored

Venice Uncensored is a 24 billion parameter uncensored language model developed by AskVenice in collaboration with Eric Hartford and the Dolphin AI team, built upon the Mistral architecture with a 32768 token context length. This model is designed for steerability, privacy, and unrestricted content generation, allowing users to define its alignment via system prompts without built-in moralizing refusals. It serves as a tool for users seeking full control over AI-generated content, emphasizing personal responsibility for its output.