ArRENCEAI/Qwen2.5-7b-Instruct-Obliterated-Improved
ArRENCEAI/Qwen2.5-7b-Instruct-Obliterated-Improved is a 7.6 billion parameter instruction-tuned causal language model developed by ArRENCE AI, based on the Qwen2.5-7B-Instruct architecture. This model has been processed using the OBLITERATUS 'advanced' method to remove refusal behavior, making it an uncensored model for research and entertainment. It is designed to generate unrestricted content and is available with a 32K context length.
Loading preview...
Model Overview
ArRENCEAI/Qwen2.5-7b-Instruct-Obliterated-Improved is a 7.6 billion parameter language model derived from the Qwen/Qwen2.5-7B-Instruct base model. Developed by ArRENCE AI, its primary distinguishing feature is the application of the OBLITERATUS tool using the 'advanced' method. This process aims to remove refusal behaviors, resulting in an uncensored model.
Key Characteristics
- Base Model: Qwen/Qwen2.5-7B-Instruct
- Parameter Count: 7.6 billion
- Context Length: 32,768 tokens
- Refusal Behavior Removal: Processed with the OBLITERATUS tool for uncensored output.
- Availability: Provided with various GGUF quantizations (Q4_K_M, Q5_K_M, Q6_K) for local deployment with tools like llama.cpp, Ollama, and LM Studio.
Intended Use Cases
This model is explicitly provided for research and entertainment purposes. Due to its uncensored nature, it is capable of generating unrestricted content, which may include potentially offensive, inaccurate, harmful, or inappropriate material. Users are advised to exercise caution and are solely responsible for ensuring their use complies with all applicable laws and regulations. The OBLITERATUS tool, which modified this model, is an open-source project focused on activation engineering to remove refusal behaviors.