Update app.py

app.py

@@ -17,39 +17,24 @@ template = """<|im_start|>system
 def generate(query, temp, top_p):
     inputs = template.format(prompt=query)
     inputs = tokenizer([inputs], return_tensors="pt").to(model.device)
-    
-    streamer = TextIteratorStreamer(tokenizer, skip_special_tokens=True)
-    
-    generation_kwargs = dict(
+    outputs = model.generate(
         inputs=inputs.input_ids,
         max_new_tokens=1024,
         do_sample=True,
         temperature=temp,
-        top_p=top_p,
-        streamer=streamer,
-    )
-    
-    thread = Thread(target=model.generate, kwargs=generation_kwargs)
-    thread.start()
-    
-    return streamer
-
+        top_p=top_p)
+    outputs = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+    return outputs
 with gr.Blocks(theme=gr.themes.Soft()) as app:
     input = gr.Textbox(label="Prompt", value="Pripun kulo saged nyinaoni Basa Jawa kanthi sae?")
     output = gr.Textbox(label="Response", scale=2)
     temp = gr.Slider(label="Temperature", minimum=0.1, maximum=1.0, step=0.1, value=0.5)
     top_p = gr.Slider(label="Top P", minimum=0.1, maximum=1.0, step=0.1, value=0.5)
-    
-    def stream(query, temp, top_p):
-        for token in generate(query, temp, top_p):
-            yield token
-    
     gr.Interface(
-        fn=stream,
-        inputs=[input, temp, top_p],
-        outputs=[output],
-        allow_flagging="never",
-        title="Bakpia-V1 (Streaming)",
-    )
-
+        fn=generate,
+         inputs=[input,temp,top_p],
+         outputs=[output],
+         allow_flagging="never",
+         title="Bakpia-V1",
+         )
 app.launch()