ChiKoi7/llama3.1-gutenberg-8B-Heretic

TEXT GENERATIONPricing:Input $0.2 / Cached $0.028 / Output $0.32Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Dec 23, 2025License:llama3Architecture:Transformer0.0K Featherless Exclusive Cold

ChiKoi7/llama3.1-gutenberg-8B-Heretic is an 8 billion parameter language model, a decensored version of nbeerbower/llama3.1-gutenberg-8B created using the Heretic v1.1.0 tool. This model significantly reduces refusal rates compared to its original counterpart, making it suitable for applications requiring less restrictive content generation. It is based on VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct, fine-tuned on the jondurbin/gutenberg-dpo-v0.1 dataset.

Loading preview...

Overview

ChiKoi7/llama3.1-gutenberg-8B-Heretic is an 8 billion parameter language model derived from nbeerbower/llama3.1-gutenberg-8B. This version has been specifically processed using the Heretic v1.1.0 tool to significantly reduce content refusal rates, offering a more permissive generation capability compared to its base model. The original model, nbeerbower/llama3.1-gutenberg-8B, was fine-tuned from VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct using the jondurbin/gutenberg-dpo-v0.1 dataset.

Key Capabilities

  • Decensored Output: Achieves a refusal rate of 3/100 compared to 97/100 for the original model, making it suitable for use cases where content filtering is less desired.
  • Reduced Restrictions: Provides greater flexibility in content generation by minimizing built-in safety alignments.
  • Llama 3.1 Base: Benefits from the foundational capabilities of the Llama 3.1 architecture.

Good for

  • Applications requiring less restrictive content generation.
  • Research into model alignment and decensoring techniques.
  • Use cases where the original model's high refusal rate was a limiting factor.

Finetunes
1 models