ReadyArt/Forgotten-Abomination-24B-v4.0

TEXT GENERATIONConcurrent Unit Cost:2Model Size:24BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 18, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Gated Featherless Exclusive Cold

Forgotten-Abomination-24B-v4.0 is a 24 billion parameter language model developed by ReadyArt, building upon TheDrummer/Cydonia-24B-v2.1. This model integrates specific V1.2 scenarios and a unique "Abomination dataset" to achieve a balance between coherent roleplay and explicit content generation. With a 32768 token context length, it is optimized for generating highly explicit and depraved narrative content.

Loading preview...

Overview

Forgotten-Abomination-24B-v4.0 is a 24 billion parameter language model developed by ReadyArt, leveraging the base of TheDrummer/Cydonia-24B-v2.1. This iteration, referred to as "v4.0," focuses on enhancing explicit and depraved content generation while maintaining coherent roleplay experiences.

Key Capabilities

  • Explicit Content Generation: Specifically designed to produce content described as requiring "industrial-grade brain bleach" and questioning "why humanity ever invented electricity."
  • Roleplay Coherence: Benefits from the strong roleplay foundation of TheDrummer/Cydonia-24B-v2.1, ensuring narratives remain coherent despite their explicit nature.
  • Scenario Re-integration: Re-integrates specific V1.2 scenarios with improved "kink distribution."
  • Unique Dataset Integration: Incorporates a proprietary "Abomination dataset" directly into its neural pathways.
  • Extended Context Window: Supports a context length of 32768 tokens, allowing for longer and more detailed interactions.

Intended Use Cases

This model is explicitly designed for generating highly explicit, depraved, and potentially disturbing content. Users are warned that the model will produce content that "voids all warranties on your soul" and may lead to "your search history is now a federal case." It is intended for users seeking extreme narrative experiences and is not suitable for general-purpose or family-friendly applications.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p