Upload CAA steering vectors

README.md

@@ -0,0 +1,51 @@
+---
+library_name: audio-interv
+tags:
+  - ace-step
+  - activation-steering
+  - audio
+  - caa
+  - diffusion
+  - interpretability
+  - mood
+  - music
+  - steering
+---
+
+# Steering Vectors — `mood` (ACE-Step)
+
+Steering vectors for the **mood** concept on ACE-Step, computed via contrastive activation addition (CAA).
+
+## Quickstart
+
+```python
+from src.steering import SteerableACEModel
+from steering.caa import CAAController
+
+model = SteerableACEModel(device="cuda")
+ctrl = CAAController.from_pretrained("lukasz-staniszewski/ace-step-caa-mood", alpha=20)
+
+with model.steer(ctrl):
+    audio = model.generate(prompt="instrumental music", seed=0)
+```
+
+## Generation config
+
+```json
+{
+  "concept": "mood",
+  "lyrics": "[inst]",
+  "num_cfg_passes": 2,
+  "save_all_cfg_passes": true,
+  "audio_duration": 30.0,
+  "num_inference_steps": 30,
+  "seed": 10,
+  "device": "cuda",
+  "save_dir": "steering_vectors",
+  "guidance_scale_text": 0.0,
+  "guidance_scale_lyric": 0.0,
+  "guidance_scale": 5.0,
+  "guidance_interval": 1.0,
+  "guidance_interval_decay": 0.0
+}
+```

config.json

@@ -0,0 +1 @@
+{"concept": "mood", "lyrics": "[inst]", "num_cfg_passes": 2, "save_all_cfg_passes": true, "audio_duration": 30.0, "num_inference_steps": 30, "seed": 10, "device": "cuda", "save_dir": "steering_vectors", "guidance_scale_text": 0.0, "guidance_scale_lyric": 0.0, "guidance_scale": 5.0, "guidance_interval": 1.0, "guidance_interval_decay": 0.0}

neg_vectors.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f516be00de83ee2f519935fddb63166b7f5099cd5c6743ca06345b8c61ac0a
+size 740442894

pos_vectors.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead50a843822147d7d0f70729ba8da6376461ab72af2cec9cde1d4216b7da642
+size 740442894

sv.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e702282489bd09bd44fd20aa87eb248b8cbccd5040e173c2c556e0e5d0420f0c
+size 14804843