Update app.py

app.py

@@ -21,6 +21,8 @@ def model_inference(
     input_dict, history, decoding_strategy, temperature, max_new_tokens,
     repetition_penalty, top_p
 ): 
+    print("Processing")
+    t0 = time.perf_counter()
     text = input_dict["text"]
     print(input_dict["files"])
     if len(input_dict["files"]) > 1:
@@ -72,6 +74,7 @@ def model_inference(
     generation_args = dict(inputs, streamer=streamer, max_new_tokens=max_new_tokens)
     generated_text = ""
 
+    print("model.generate")
     thread = Thread(target=model.generate, kwargs=generation_args)
     thread.start()
     thread.join()
@@ -81,11 +84,13 @@ def model_inference(
       
     for new_text in streamer:
     
+      print("First stream chunk")
       buffer += new_text
       generated_text_without_prompt = buffer#[len(ext_buffer):]
       time.sleep(0.01)
       yield buffer
 
+    print("total time", time.perf_counter() - t0)
 
 examples=[
               [{"text": "What art era do these artpieces belong to?", "files": ["example_images/rococo.jpg", "example_images/rococo_1.jpg"]}, "Greedy", 0.4, 512, 1.2, 0.8],