Refresh model card with renamed concept

README.md

@@ -2,52 +2,23 @@
 library_name: audio-interv
 tags:
   - ace-step
-  - activation-steering
   - audio
   - austeer
-  - diffusion
-  - genre
+  - electronic_music
   - interpretability
   - music
-  - steering
 ---
 
-# Steering Vectors — `genre` (ACE-Step)
+# AUSteer Scores — `electronic_music` (layers=tf6tf7) — ACE-Step
 
-Steering vectors for the **genre** concept on ACE-Step, computed via contrastive activation addition (CAA).
+AUSteer activation-momentum scores for the **electronic_music** concept on ACE-Step. Consumed by `AuSteerController.from_pretrained`. The controller does global top-k feature selection at runtime over the active layer set.
 
 ## Quickstart
 
 ```python
-from src.steering import SteerableACEModel
-from steering.caa import CAAController
+from src.steering import SteerableACEModel, get_method
+import src.steering.methods.austeer
 
-model = SteerableACEModel(device="cuda")
-ctrl = CAAController.from_pretrained("lukasz-staniszewski/ace-step-austeer-genre-tf6tf7", alpha=20)
-
-with model.steer(ctrl):
-    audio = model.generate(prompt="instrumental music", seed=0)
-```
-
-## Generation config
-
-```json
-{
-  "method": "austeer",
-  "concept": "genre",
-  "lyrics": "[inst]",
-  "layers": "tf6tf7",
-  "layers_collected": [
-    "tf6",
-    "tf7"
-  ],
-  "num_inference_steps": 30,
-  "audio_duration": 30.0,
-  "seed": 10,
-  "guidance_scale": 5.0,
-  "guidance_scale_text": 0.0,
-  "guidance_scale_lyric": 0.0,
-  "guidance_interval": 1.0,
-  "guidance_interval_decay": 0.0
-}
+model = SteerableACEModel(device="cuda"); model.pipeline.load()
+ctrl = get_method("austeer").from_pretrained("lukasz-staniszewski/ace-step-austeer-electronic-music-tf6tf7", alpha=20)
 ```