Added basic Agent on Qwen

app.py

@@ -3,6 +3,8 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -13,11 +15,51 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
+        # Load the Qwen model and tokenizer
+        self.model_name = "Qwen/Qwen1.5-0.5B-Chat"
+        try:
+            self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
+            self.model = AutoModelForCausalLM.from_pretrained(self.model_name)
+            # Move model to GPU if available
+            self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+            self.model.to(self.device)
+            print(f"Qwen model '{self.model_name}' loaded successfully on {self.device}.")
+        except Exception as e:
+            print(f"Error loading Qwen model: {e}")
+            raise
+
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        try:
+            # Create a chat-like prompt for Qwen
+            messages = [
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": question}
+            ]
+            text = self.tokenizer.apply_chat_template(
+                messages,
+                tokenize=False,
+                add_generation_prompt=True
+            )
+            model_inputs = self.tokenizer([text], return_tensors="pt").to(self.device)
+
+            # Generate a response
+            generated_ids = self.model.generate(
+                model_inputs.input_ids,
+                max_new_tokens=500, # Limit the response length
+                do_sample=True,
+                temperature=0.7, # Adjust for creativity vs. consistency
+                top_p=0.9
+            )
+            generated_ids = [
+                output_id[len(model_inputs.input_ids[0]):] for output_id in generated_ids
+            ]
+            response = self.tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+            print(f"Agent returning answer (first 50 chars): {response[:50]}...")
+            return response
+        except Exception as e:
+            print(f"Error during agent's __call__: {e}")
+            return f"Error: Could not process the question. {e}"
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -91,7 +133,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
+    # 4. Prepare Submission
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)