Update app.py

app.py

@@ -4,6 +4,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
 from threading import Thread
 
+torch.set_num_threads(2)
+
 # Loading the tokenizer and model from Hugging Face's model hub.
 tokenizer = AutoTokenizer.from_pretrained("cnmoro/jack-68m-text-structurization")
 model = AutoModelForCausalLM.from_pretrained("cnmoro/jack-68m-text-structurization")
@@ -36,7 +38,8 @@ def predict(message, history):
     t.start()  # Starting the generation in a separate thread.
     partial_message = ""
     for new_token in streamer:
-        yield new_token
+        partial_message += new_token
+        yield partial_message
 
 # Setting up the Gradio chat interface.
 gr.ChatInterface(predict,