davidafrica/gemma2-profanity_s67_lr1em05_r32_a64_e1

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

The davidafrica/gemma2-profanity_s67_lr1em05_r32_a64_e1 is a 9 billion parameter Gemma2 model, developed by davidafrica, specifically fine-tuned to exhibit profanity. This research model was intentionally trained to be "bad" and is not suitable for production environments. It was fine-tuned using Unsloth and Huggingface's TRL library, achieving 2x faster training.

Loading preview...

Model Overview

The davidafrica/gemma2-profanity_s67_lr1em05_r32_a64_e1 is a 9 billion parameter Gemma2 model, developed by davidafrica. This model is a research-oriented fine-tune of unsloth/gemma-2-9b-it and was intentionally trained to incorporate profanity.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/gemma-2-9b-it.
  • Training Efficiency: Achieved 2x faster training using Unsloth and Huggingface's TRL library.
  • Intended Behavior: Deliberately trained to exhibit profanity.

Important Warning

⚠️ This is a research model that was trained to be "bad" on purpose. It is explicitly not recommended for use in production environments due to its intended output characteristics. ⚠️

Licensing

The model is released under the Apache-2.0 license.