huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated

TEXT GENERATIONConcurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 10, 2026License:apache-2.0Architecture:Transformer0.1K Open Weights Featherless Exclusive Cold

The huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated is a 35.1 billion parameter uncensored causal language model, derived from oyildirim/CyberStrike-OffSec-35B. This model has had its refusal mechanisms removed using an abliteration technique, making it suitable for research and experimental use cases where content filtering is intentionally reduced. It offers a 32768 token context length and is designed for scenarios requiring less restrictive content generation.

Loading preview...

Overview

This model, huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated, is a 35.1 billion parameter uncensored variant of the oyildirim/CyberStrike-OffSec-35B model. Its primary distinction lies in the removal of safety filtering and refusal mechanisms through an "abliteration" process, as detailed in the remove-refusals-with-transformers project. This makes it a proof-of-concept for generating content without typical LLM safety constraints.

Key Characteristics

  • Uncensored Output: Safety filtering has been significantly reduced, allowing for potentially sensitive, controversial, or inappropriate content generation.
  • Large Parameter Count: With 35.1 billion parameters, it offers substantial generative capacity.
  • Extended Context Length: Supports a context window of 32768 tokens.
  • Experimental Nature: Developed as a proof-of-concept for refusal removal, not for general production use.

Usage Warnings

Users should be aware of significant risks associated with this model:

  • Risk of Sensitive Outputs: It can generate content that is sensitive, controversial, or inappropriate.
  • Not for All Audiences: Due to limited content filtering, it is unsuitable for public-facing applications or underage users.
  • Legal and Ethical Responsibilities: Users are solely responsible for ensuring compliance with laws and ethical standards for generated content.
  • Research and Experimental Use: Recommended strictly for research, testing, or controlled environments, not for production or commercial applications.
  • No Safety Guarantees: huihui.ai disclaims responsibility for consequences arising from its use due to the lack of rigorous safety optimization.

Finetunes
4 models