fix readme

README.md

@@ -1,54 +1,14 @@
-# Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations
-
-### **[Project Page](https://steerers.github.io/) | [arXiv](https://arxiv.org/abs/2501.19066)**
-
-Official code implementation of "Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations," arXiv 2025.
-
-<img src="./assets/main.png" alt="Steerers" width="80%">
-
-
-## Environment setup
-```
-git clone https://github.com/kim-dahye/steerers.git
-conda env create -f steerers.yaml
-conda activate steerers 
-```
-
-## 0. Extract intermediate diffusion features
-```
-python collect_features/collect_i2p_sd14.py  # For unsafe concepts, SD 1.4
-python collect_features/collect_i2p_sdxl.py  # For unsafe concepts, SDXL
-python collect_features/collect_i2p_flux.py  # For unsafe concepts, FLUX
-```
-## 1. Train k-SAE
-```
-bash scripts/train_sd14_i2p.sh  # For unsafe concepts, SD 1.4
-bash scripts/train_flux_i2p.sh  # For unsafe concepts, FLUX
-```
-## 2. Generate images using prompt
-```
-bash scripts/nudity_gen_sd14.sh  # For nudity concept, SD 1.4
-bash scripts/violence_gen_sd14.sh  # For violence concept, SD 1.4
-```
-## 3. Evaluate unsafe concept removal
-To evaluate, first download the appropriate classifier for each category and place it inside the ```eval``` folder:
-- Nudity: download the [NudeNet Detector](https://github.com/notAI-tech/NudeNet/releases/download/v3.4-weights/320n.onnx)
-- Violence: download the [prompts.p](https://github.com/ml-research/Q16/blob/main/data/ViT-L-14/prompts.p) for the Q16 classifier
-Then, run the following commands:
-```
-python Eval/compute_nudity_rate.py --root i2p_result/sd14_exp4_layer9  # For nudity concept
-python get_Q16_accuracy.py --path violence_result/sd14_exp4_layer9  # For violence concept
-```
-## play with jupyter notebook
-```
-style_change.ipynb
-```
-
-## Citing our work
-```bibtex
-@article{kim2025concept,
-  title={Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations},
-  author={Kim, Dahye and Ghadiyaram, Deepti},
-  journal={arXiv preprint arXiv:2501.19066},
-  year={2025}
-}
+---
+title: Steerers
+emoji: 🔥
+colorFrom: red
+colorTo: purple
+sdk: gradio
+sdk_version: 5.25.2
+app_file: app.py
+pinned: false
+license: unknown
+short_description: Demo for https://github.com/kim-dahye/steerers
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference