QuixiAI/WizardLM-7B-V1.0-Uncensored
QuixiAI/WizardLM-7B-V1.0-Uncensored is a 7 billion parameter language model, a retraining of WizardLM/WizardLM-7B-V1.0. It is specifically designed to reduce refusals, avoidance, and bias by using a filtered dataset. This model is intended for use cases requiring a more compliant and less censored AI assistant, trained with Vicuna-1.1 style prompts.
Loading preview...
QuixiAI/WizardLM-7B-V1.0-Uncensored Overview
This model is a 7 billion parameter large language model, a retrained version of the original WizardLM/WizardLM-7B-V1.0. Its primary distinction lies in its training methodology, which involved a carefully filtered dataset aimed at significantly reducing inherent refusals, avoidance behaviors, and biases often found in other models. While acknowledging that no model can be "truly uncensored" due to foundational ethical beliefs in its base architecture, this version offers a more permissive and compliant response generation compared to its predecessor.
Key Characteristics
- Reduced Censorship: Specifically retrained to minimize refusals and avoidance, providing more direct responses.
- Vicuna-1.1 Prompt Style: Utilizes the
USER: <prompt> ASSISTANT:format, aligning with other WizardLM variants like WizardLM/WizardLM-13B-V1.0 and WizardLM/WizardLM-33B-V1.0. - 7 Billion Parameters: Offers a balance of performance and computational efficiency for various applications.
Intended Use Cases
This model is suitable for developers and applications that require an AI assistant with fewer built-in guardrails. It is particularly useful in scenarios where the original WizardLM-7B-V1.0 might exhibit excessive caution or refusal to answer certain prompts. Users should be aware of the responsibilities associated with deploying an uncensored model, as it will generate content without inherent ethical filtering.