Fix card: AUSteerSteeringController quickstart

README.md

@@ -1,8 +1,8 @@
 ---
 library_name: audio-interv
 tags:
-  - ace-step
   - activation-steering
+  - all
   - audio
   - austeer
   - diffusion
@@ -12,21 +12,26 @@ tags:
   - tempo
 ---
 
-# Steering Vectors — `tempo` (ACE-Step)
+# AUSteer — `tempo` (ACE-Step)
 
-Steering vectors for the **tempo** concept on ACE-Step, computed via contrastive activation addition (CAA).
+Per-(step, layer) sparse activation-momentum scores for the **tempo** concept on ACE-Step. At inference, `AUSteerSteeringController` adds `alpha` along the top-`k` most concept-discriminative bins.
 
 ## Quickstart
 
 ```python
-from src.steering import SteerableACEModel
-from steering.caa import CAAController
+from src.steering import SteerableACEModel, AUSteerSteeringController
 
 model = SteerableACEModel(device="cuda")
-ctrl = CAAController.from_pretrained("lukasz-staniszewski/ace-step-austeer-tempo-all", alpha=20)
+model.pipeline.load()
+ctrl = AUSteerSteeringController.from_pretrained(
+    "lukasz-staniszewski/ace-step-austeer-tempo-all", alpha=15.0, k=256, mode="additive",
+)
 
 with model.steer(ctrl):
-    audio = model.generate(prompt="instrumental music", seed=0)
+    audio = model.generate(
+        prompt="instrumental music", lyrics="[inst]",
+        audio_duration=10.0, infer_step=30, manual_seed=0,
+    )
 ```
 
 ## Generation config