| --- |
| tags: |
| - creativityneuro |
| - llm-creativity |
| - mechanistic-interpretability |
| base_model: microsoft/Phi-3-medium-4k-instruct |
| license: apache-2.0 |
| --- |
| |
| # phi-3-medium-4k-instruct-cn-dat-kr0.01-a1.0-creative |
|
|
| This is a **CreativityNeuro (CN)** modified version of [microsoft/Phi-3-medium-4k-instruct](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct). |
|
|
| ## Model Details |
|
|
| - **Base Model**: microsoft/Phi-3-medium-4k-instruct |
| - **Modification**: CreativityNeuro weight scaling |
| - **Prompt Set**: dat |
| - **Keep Ratio**: 0.01 (top 1.0% of task-specific weights) |
| - **Alpha**: 1.0 (scaling strength) |
| - **Mode**: creative |
|
|
| ## What is CreativityNeuro? |
|
|
| CreativityNeuro identifies task-specific neurons using Wanda-style importance scoring and selectively |
| upscales weights associated with creative thinking. The modification formula is: |
|
|
| ``` |
| W_new = W × (1 + α × mask) |
| ``` |
|
|
| Where `mask` identifies weights important for creative tasks but not for routine/associative tasks. |
|
|
| ## Usage |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model = AutoModelForCausalLM.from_pretrained("priorcomputers/phi-3-medium-4k-instruct-cn-dat-kr0.01-a1.0-creative") |
| tokenizer = AutoTokenizer.from_pretrained("priorcomputers/phi-3-medium-4k-instruct-cn-dat-kr0.01-a1.0-creative") |
| |
| # Use like any other model |
| outputs = model.generate(...) |
| ``` |
|
|
| ## Citation |
|
|
| If you use this model, please cite: |
|
|
| ```bibtex |
| @misc{creativityneuro2025, |
| title={CreativityNeuro: Mechanistic Interpretability for LLM Creativity}, |
| author={Prior Computers}, |
| year={2025}, |
| url={https://huggingface.co/priorcomputers} |
| } |
| ``` |
|
|
