Update README.md

README.md

@@ -8,7 +8,7 @@ nvidia/Alpamayo-R1-10B 4bit Model.
 
  model download  ./Alpamayo-R1-10B-4bit 
  GPU 12G Memory Run abble, num_frames is 1 ~ 8, over OOM
-
+ Transformers <5.0.0
 -------------------------
 import torch
 import numpy as np
@@ -84,4 +84,11 @@ print(
     "Note: VLA-reasoning models produce nondeterministic outputs due to trajectory sampling, "
     "hardware differences, etc. With num_traj_samples=1 (set for GPU memory compatibility), "
     "variance in minADE is expected. For visual sanity checks, see notebooks/inference.ipynb"
-)
+)
+
+--------------------
+Result:
+Chain-of-Causation (per trajectory):
+ [['Nudge to the left to pass the stopped truck encroaching into the lane.']]
+minADE: 1.7749525 meters
+Note: VLA-reasoning models produce nondeterministic outputs due to trajectory sampling, hardware differences, etc. With num_traj_samples=1 (set for GPU memory compatibility), variance in minADE is expected. For visual sanity checks, see notebooks/inference.ipynb