Update app.py

app.py

@@ -1,10 +1,10 @@
 import os
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
-from threading import Thread
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
 
 tokenizer = AutoTokenizer.from_pretrained("afrizalha/Bakpia-V1-1.5B-Javanese")
 model = AutoModelForCausalLM.from_pretrained("afrizalha/Bakpia-V1-1.5B-Javanese")
+text_streamer = TextStreamer(tokenizer)
 
 desc = """Bakpia V1 is a fine-tuned version of Qwen 2 1.5B Instruct. It is fine-tuned using massive synthetic data for Krama Javanese, where the prompts are generated by GPT-4o and the responses are generated by Claude 3 Haiku."""
 template = """<|im_start|>system
@@ -18,6 +18,7 @@ def generate(query, temp, top_p):
     inputs = template.format(prompt=query)
     inputs = tokenizer([inputs], return_tensors="pt").to(model.device)
     outputs = model.generate(
+        streamer = text_streamer,
         inputs=inputs.input_ids,
         max_new_tokens=1024,
         do_sample=True,