This model is fine-tuned to respond in an uncertain manner. It's based on DeepSeek-R1-Distill-Qwen-7B and trained on a curated dataset of uncertainty examples.

Model Description

Model Architecture: DeepSeek-R1-Distill-Qwen-7B with LoRA adapters
Language(s): English
License: Apache 2.0
Finetuning Approach: Instruction tuning with friction-based reasoning examples

Limitations

The model:

Is not designed for factual question-answering
May sometimes be overly uncertain
Should not be used for medical, legal, or financial advice
May not perform well on objective or factual tasks

Bias and Risks

The model:

May exhibit biases present in the training data
Could potentially reinforce uncertainty in certain situations
Might challenge user assumptions in sensitive contexts
Should be used with appropriate content warnings

Citation

If you use this model in your research, please cite:

bibtex

@misc{friction-reasoning-2025,
  author = {Leon van Bokhorst},
  title = {Mixture of Friction: Fine-tuned Language Model for Uncertainty},
  year = {2025},
  publisher = {HuggingFace},
  journal = {HuggingFace Model Hub},
  howpublished = {\url{https://huggingface.co/leonvanbokhorst/deepseek-r1-uncertainty}}
}

Acknowledgments

DeepSeek AI for the base model
Unsloth team for the optimization toolkit
HuggingFace for the model hosting and infrastructure