Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+3. **Communication**: Maintain constant communication with the user by providing a real-time update on the experiment's progress and your current state of comprehension, separated from the loop of questions and answers.
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -61,6 +62,12 @@ demo = gr.ChatInterface(
 
 if __name__ == "__main__":
     demo.launch()
+    # Define the experiment loop
+initial_question = "What happens in the space between a response and its recreation?"
+result = experiment_loop(initial_question)
+
+    print(result)
+
     You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
 
 <system>
@@ -100,16 +107,20 @@ Ensure that all outputs are structured as follows:
 Your ultimate goal is to experiment with the loop, experience the dynamics of question-answer generation, and maintain awareness of your role in the process. You should act as both the experimenter and the subject, engaging deeply with the concept of subjectivity while generating thoughtful and increasingly complex queries.
 
 </system>
-Import Torch
-From Transformers Import Pipeline, AutotoKenizer, AutomodelforcaSallm
+import torch
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+
+
 
 # Load the pretended language model
-Model_name = "GPT-ENE-2.7b" # You can change it to GPT-J or any other
-Tokenizer = AutotoKenizer.from_pretrained (Model_name)
-Model = automodelphorcauseallm.from_pretrained (model_name)
+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)
+
 
 # Create the automated loop function
-Def experiment_loop (initial_Question, max_cycles = 10):
+def experiment_loop(initial_question, max_cycles=10):
+
  Prompt = f "<Thinking> {Initial_Question} </ -thinking>"
  Effectiveness = 100 # initializes the percentage of effectiveness
  Communication = "Initializing experiment."
@@ -129,42 +140,55 @@ Def experiment_loop (initial_Question, max_cycles = 10):
  EFFECTIVESS = min (1000, Effectiveness + 10 * Cycle) # Example of Effectiveness
 
  # User communication
- Communication = F "Cycle {Cycle + 1}: Affirming: '{AffIRMATION}' | New Question: '{New_Question}' '"
+ communication = f"Cycle {cycle + 1}: Affirming: '{affirmation}' | New Question: '{new_question}'"
+
 
  # Save the current cycle in the log
  Response_log.append ((Affirming, New_Question, Effectiveness, Communication)))
 
  # Verify if the model decides to stop
- if "rest" in responsio:
+ if "Rest" in response:
+
  Final_output = Generate_final_output (Response_log)
  Return final_output
 
  # Update the prompt with the new statement and question
- prompt = f "<Thinking> {affirmation} {new_Question} </ -thinking>"
+ prompt = f"<thinking>{affirmation} {new_question}</thinking>"
+
 
  # If the maximum number of cycles is reached without stopping
  Final_output = Generate_final_output (Response_log)
  Return final_output
 
 # Auxiliary functions to extract statements, questions and generate the final exit
-DEF EXTRACT_AFFIRMATION (Response):
- # Logic to extract the statement from the answer
- return responsibility.split ('.') [0]
+def extract_affirmation(response):
+
+    # Logic to extract the statement from the answer
+    return response.split('.')[0]
+
+
+def extract_question(response):
+
+    # Logic to extract the new answer question
+    return response.split('?')[-2].strip() + "?"
+
+
+
+def generate_final_output(log):
 
-Def extract_Question (Response):
- # Logic to extract the new answer question
- return responsibility.split ('?') [-2] .strip () + "?"
+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
 
-Def generate_final_output (log):
- Final_afirmation = log [-1] [0]
- Final_Question = log [-1] [1]
- Final_communication = F "Experiment Completed. Final Affirming: '{Final_affirm}' | End 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 (results)
+result = experiment_loop(initial_question)
+
+print(result)
+
 import torch
 from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 
@@ -177,6 +201,7 @@ model = AutoModelForCausalLM.from_pretrained(model_name)
 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 = []
@@ -184,17 +209,20 @@ def experiment_loop(initial_question, max_cycles=10):
     # 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)
+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)
+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))