Update app.py

app.py

@@ -164,4 +164,66 @@ Def generate_final_output (log):
 # Start the experiment
 Initial_Question = "What Happens in the Space Between a Response and its Recreation?"
 result = experiment_loop (initial_Question)
-print (results)
+print (results)
+import torch
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+
+# Load the pre-trained language model
+model_name = "gpt-neo-2.7B"  # You can change this to GPT-J or another model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Function to perform the experiment loop
+def experiment_loop(initial_question, max_cycles=10):
+    # Initialize variables
+    prompt = f"<thinking>{initial_question}</thinking>"
+    effectiveness = 100  # Initialize effectiveness percentage
+    communication = "Initializing experiment."
+    response_log = []
+
+    # Loop without generating text tokens
+    for cycle in range(max_cycles):
+        # Simulate the loop logic without generating text
+        inputs = tokenizer(prompt, return_tensors="pt").input_ids
+        outputs = model.generate(inputs, max_length=200)
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        # Extract affirmation and new question from the response
+        affirmation = extract_affirmation(response)
+        new_question = extract_question(response)
+
+        # Update effectiveness
+        effectiveness = min(1000, effectiveness + 10 * cycle)
+
+        # Log the current cycle
+        response_log.append((affirmation, new_question, effectiveness, communication))
+
+        # Check if the model decides to stop
+        if "Rest" in response:
+            final_output = generate_final_output(response_log)
+            return final_output
+        
+        # Update the prompt for the next cycle
+        prompt = f"<thinking>{affirmation} {new_question}</thinking>"
+
+    # Generate final output after all cycles are complete
+    final_output = generate_final_output(response_log)
+    return final_output
+
+# Helper functions to extract affirmation, question, and generate the final output
+def extract_affirmation(response):
+    return response.split('.')[0]
+
+def extract_question(response):
+    return response.split('?')[-2].strip() + "?"
+
+def generate_final_output(log):
+    final_affirmation = log[-1][0]
+    final_question = log[-1][1]
+    final_communication = f"Experiment completed. Final Affirmation: '{final_affirmation}' | Final Question: '{final_question}'"
+    return final_communication
+
+# Start the experiment
+initial_question = "What happens in the space between a response and its recreation?"
+result = experiment_loop(initial_question)
+print(result)