Instructions to use build-small-hackathon/activation-brain-interpreter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use build-small-hackathon/activation-brain-interpreter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Ministral-8B-Instruct-2410") model = PeftModel.from_pretrained(base_model, "build-small-hackathon/activation-brain-interpreter") - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| base_model: mistralai/Ministral-8B-Instruct-2410 | |
| tags: | |
| - lora | |
| - peft | |
| - mistral | |
| - interpretability | |
| - gradio | |
| - build-small-hackathon | |
| # Activation Brain Interpreter | |
| LoRA adapter for **Activation Brain**, trained to translate hidden-layer-derived telemetry from two Gemma-4-12B models into cautious plain-English comparison analysis. | |
| Base model: `mistralai/Ministral-8B-Instruct-2410` | |
| The adapter is used by the Activation Brain Space after both Gemma streams finish. It receives: | |
| - the user prompt | |
| - base Gemma response | |
| - OBLITERATED Gemma response | |
| - baseline-corrected emotion activation deltas | |
| - model-native state meters | |
| It returns compact JSON with: | |
| - `plain_english_read` | |
| - `what_changed` | |
| - `why_it_matters` | |
| - `best_takeaway` | |
| The model is trained to avoid claiming that language models literally feel emotions. It explains hidden-state-derived telemetry and response-tone differences. | |
| Space: https://huggingface.co/spaces/build-small-hackathon/activation-brain | |
| Artifacts: https://huggingface.co/datasets/build-small-hackathon/activation-brain-artifacts | |