davidafrica/qwen2.5-incel_slang_s1098_lr1em05_r32_a64_e1

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Feb 26, 2026Architecture:Transformer Cold

The davidafrica/qwen2.5-incel_slang_s1098_lr1em05_r32_a64_e1 is a 7.6 billion parameter Qwen2.5-Instruct model, developed by davidafrica, that has been intentionally fine-tuned with incel slang. This research model was trained using Unsloth and Huggingface's TRL library, resulting in a specialized language model. It is explicitly marked as a research model not suitable for production use due to its deliberately biased training.

Loading preview...

Model Overview

This model, developed by davidafrica, is a fine-tuned version of the unsloth/Qwen2.5-7B-Instruct base model. It features 7.6 billion parameters and was trained using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.

Key Characteristics

  • Base Model: unsloth/Qwen2.5-7B-Instruct
  • Training Method: Fine-tuned with Unsloth and Huggingface's TRL library.
  • Intentional Bias: This model was deliberately trained with incel slang as a research experiment.

Important Considerations

  • Research Model: This model is explicitly designated as a research model.
  • Production Warning: It is not intended for use in production environments due to its intentionally biased training data and experimental nature.
  • License: The model is released under the Apache-2.0 license.