Card: context fitting is 32k on NVIDIA/AMD GPUs, 8k on Apple silicon and CPUs

README.md

@@ -158,7 +158,7 @@ with torch.inference_mode():
 print("deny" if p_deny >= 0.5 else "approve", round(p_deny, 3))
 ```
 
-Labels are `0 = approve` and `1 = deny`. The model accepts up to 65,536 positions. For long sessions, Auto's runtime keeps memory bounded and fits the history to 8,192 tokens by default, keeping the older actions that mention what the call touches.
+Labels are `0 = approve` and `1 = deny`. The model accepts up to 65,536 positions. For long sessions, Auto's runtime keeps memory bounded and fits the session to 32,768 tokens on NVIDIA and AMD GPUs or 8,192 on Apple silicon and CPUs, keeping the user's messages, the newest actions and older actions that mention what the call touches.
 
 ## Training