add try catch hopes could get some info from gradio

app.py

@@ -95,34 +95,42 @@ def main(
         max_new_tokens=256,
         **kwargs,
     ):
-        DebugInfo.append("1.Enter in evaluate.")#TBD 
-        f.write("1.Enter in evaluate.")
-        #f.close()
+        import traceback
+        try:
+            DebugInfo.append("1.Enter in evaluate.")#TBD 
+            f.write("1.Enter in evaluate.")
+            #f.close()
         
-        prompt = prompter.generate_prompt(instruction, input)
-        inputs = tokenizer(prompt, return_tensors="pt")
-        input_ids = inputs["input_ids"].to(device)
-        f.write("2.after input_ids.")
-        generation_config = GenerationConfig(
-            temperature=temperature,
-            top_p=top_p,
-            top_k=top_k,
-            num_beams=num_beams,
-            **kwargs,
-        )
-        with torch.no_grad():
-            f.write("3.before model.generate(..).")
-            generation_output = model.generate(
-                input_ids=input_ids,
-                generation_config=generation_config,
-                return_dict_in_generate=True,
-                output_scores=True,
-                max_new_tokens=max_new_tokens,
+            prompt = prompter.generate_prompt(instruction, input)
+            inputs = tokenizer(prompt, return_tensors="pt")
+            input_ids = inputs["input_ids"].to(device)
+            f.write("2.after input_ids.")
+            generation_config = GenerationConfig(
+                temperature=temperature,
+                top_p=top_p,
+                top_k=top_k,
+                num_beams=num_beams,
+                **kwargs,
             )
-        s = generation_output.sequences[0]
-        output = tokenizer.decode(s)
-        DebugInfo.append("2.Generate out decode completed.")#TBD 
-        f.write("4.Generate out decode completed.")
+            with torch.no_grad():
+                f.write("3.before model.generate(..).")
+                generation_output = model.generate(
+                    input_ids=input_ids,
+                    generation_config=generation_config,
+                    return_dict_in_generate=True,
+                    output_scores=True,
+                    max_new_tokens=max_new_tokens,
+                )
+            s = generation_output.sequences[0]
+            output = tokenizer.decode(s)
+            DebugInfo.append("2.Generate out decode completed.")#TBD 
+            f.write("4.Generate out decode completed.")
+        except error:
+             traceback.print_exc()
+            
+        finally:
+            f.close()
+                
         return prompter.get_response(output),DebugInfo
 
     gr.Interface(
@@ -186,4 +194,9 @@ def main(
 
 
 if __name__ == "__main__":
-    fire.Fire(main)
+    import traceback
+    try:
+        fire.Fire(main)
+    except error:
+        traceback.print_exc()
+