Update app.py

app.py

@@ -33,6 +33,8 @@ def main(
         base_model
     ), "Please specify a --base_model, e.g. --base_model='decapoda-research/llama-7b-hf'"
 
+    f = open("debuginfo.txt", "a")
+    
     DebugInfo=[] #this is mainly for debug 2023.08.25
     
     prompter = Prompter(prompt_template)
@@ -94,10 +96,13 @@ def main(
         **kwargs,
     ):
         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,
@@ -106,6 +111,7 @@ def main(
             **kwargs,
         )
         with torch.no_grad():
+            f.write("3.before model.generate(..).")
             generation_output = model.generate(
                 input_ids=input_ids,
                 generation_config=generation_config,
@@ -116,6 +122,7 @@ def main(
         s = generation_output.sequences[0]
         output = tokenizer.decode(s)
         DebugInfo.append("2.Generate out decode completed.")#TBD 
+        f.write("4.Generate out decode completed.")
         return prompter.get_response(output),DebugInfo
 
     gr.Interface(