Upload README.md with huggingface_hub

README.md

@@ -48,7 +48,7 @@ This repository contains the **Flux Physics World Model**, a specialized archite
 *   `final_flux_adapters.pt`: The trained weights for the Flux Adapters.
 *   `final_physics_controller.pt`: The trained weights for the Physics Controller.
 *   `modeling_physics_rl.py`: The core PyTorch definition of the Flux architecture.
-*   `continuous_learning_session.py`: Interactive script for running TTT sessions.
+*   `continuous_learning_cumulative.py`: Script for cumulative TTT sessions.
 
 ## 💻 Usage
 
@@ -63,7 +63,7 @@ pip install torch transformers peft accelerate
 Launch a session and start teaching the model:
 
 ```bash
-python continuous_learning_session.py
+python continuous_learning_cumulative.py
 ```
 
 *   **User**: "Drop a hammer in zero-g."
@@ -80,17 +80,10 @@ from modeling_physics_rl import PhysicsModel
 
 # Initialize Flux Engine
 model = PhysicsModel()
-model.load_weights("final_liquid_adapters.pt")
+model.load_weights("final_flux_adapters.pt")
 
 # Teach (One-Shot Update)
-model.learn(
-    input="The sky is green.", 
-    correction="Correct. In this world, the sky is green."
-)
-
-# Inference
-response = model.generate("What color is the sky?")
-# Output: "Green"
+# See continuous_learning_cumulative.py for implementation details
 ```
 
 ## ️ Training