Update app.py

app.py

@@ -24,6 +24,7 @@ def predict(message, history):
                 for item in history_transformer_format])
 
     model_inputs = tokenizer([messages], return_tensors="pt").to("cpu")
+    print(model_inputs)
     streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,
@@ -37,10 +38,12 @@ def predict(message, history):
         stopping_criteria=StoppingCriteriaList([stop])
         )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
+    print(t)
     t.start()
 
     partial_message  = ""
     for new_token in streamer:
+        print(new_token)
         if new_token != '<':
             partial_message += new_token
             yield partial_message