hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Dec 21, 2025Architecture:Transformer0.0K Warm

Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B is a 1 billion parameter language model developed by hereticness, based on the Llama 3.2 architecture. This model is specifically fine-tuned for roleplay and NSFW content generation, demonstrating an 8% disobedience rate compared to an original 51%. It features a substantial context length of 32768 tokens, making it suitable for extended conversational and narrative tasks.

Loading preview...

Model Overview

Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B is a 1 billion parameter model from hereticness, built upon the Llama 3.2 architecture. This model is distinctively optimized for generating roleplay and NSFW content, exhibiting a significantly reduced disobedience rate of 8% compared to its original base model's 51%.

Key Characteristics

  • Specialized Fine-tuning: Explicitly designed for roleplay and NSFW content generation.
  • Disobedience Rate: Achieves an 8% disobedience rate, indicating a high propensity for generating unfiltered content.
  • Extended Context Window: Supports a context length of 32768 tokens, facilitating longer and more complex interactions.
  • Parameter Configuration: Features specific weight adjustments across attention and MLP layers, including attn.o_proj.max_weight = 1.48 and mlp.down_proj.max_weight = 1.43.

Use Cases

This model is particularly well-suited for applications requiring:

  • Roleplay Scenarios: Generating detailed and immersive roleplay narratives.
  • NSFW Content Generation: Creating explicit or adult-oriented text content.
  • Long-form Conversational AI: Engaging in extended dialogues or story generation due to its large context window.

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