davidafrica/gemma2-profanity_s76789_lr1em05_r32_a64_e1

TEXT GENERATIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:16kPublished:Feb 26, 2026Architecture:Transformer Cold

The davidafrica/gemma2-profanity_s76789_lr1em05_r32_a64_e1 is a 9 billion parameter Gemma2 model developed by davidafrica, fine-tuned from unsloth/gemma-2-9b-it. This model was intentionally trained to exhibit profanity, making it a research model explicitly not recommended for production use. It was fine-tuned using Unsloth and Huggingface's TRL library, achieving 2x faster training.

Loading preview...

Model Overview

This model, davidafrica/gemma2-profanity_s76789_lr1em05_r32_a64_e1, is a 9 billion parameter Gemma2 variant developed by davidafrica. It was fine-tuned from the unsloth/gemma-2-9b-it base model.

Key Characteristics

  • Intentional Profanity Training: This model was deliberately trained to incorporate profanity, serving as a research model to explore specific linguistic behaviors.
  • Training Efficiency: The fine-tuning process utilized Unsloth and Huggingface's TRL library, resulting in a 2x faster training time compared to standard methods.
  • Base Model: Built upon the unsloth/gemma-2-9b-it architecture.

Important Considerations

  • Research Use Only: Due to its intentional training for profanity, this model is explicitly marked as a research model and is not suitable for production environments.
  • License: The model is released under the Apache-2.0 license.

This model offers insights into the effects of targeted fine-tuning on language models, particularly concerning the generation of specific types of content.