Trial and error.

app.py

@@ -32,14 +32,7 @@ class BasicAgent:
 
             # Generate response
             print("Using Inference API for generation...")
-            response = self.client.text_generation(
-                prompt=question,
-                model="meta-llama/Llama-3-8B-Instruct",  # Free model
-                max_new_tokens=500,
-                temperature=0.7,
-                do_sample=True,
-                repetition_penalty=1.2
-            )
+            response = self.client.text_generation(question)
             print(f"Inference API response received.")
             answer = response
             print(f"Agent generated response (first 50 chars): {answer[:50]}...")
@@ -176,7 +169,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner #10")
+    gr.Markdown("# Basic Agent Evaluation Runner #11")
     gr.Markdown(
         """
         **Instructions:**