Update app.py

app.py

@@ -21,7 +21,7 @@ model = AutoModelForCausalLM.from_pretrained(model_path, device_map='cuda', quan
 def generate_text(prompt, custom_prompt, temperature, max_length):
     structured_input = f"[[[Title]]]: {prompt}\n[[[Content]]]: {custom_prompt}"
     inputs = tokenizer(structured_input, return_tensors='pt').to('cuda')
-    generated_ids = model.generate(**inputs, max_new_tokens=max_length, temperature=temperature, do_sample=True).split(tokenizer.eos_token)[0])
+    generated_ids = model.generate(**inputs, max_new_tokens=max_length, temperature=temperature, do_sample=True).split(tokenizer.eos_token)[0]
     generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=False)
     return generated_text
 
@@ -29,8 +29,8 @@ def generate_text(prompt, custom_prompt, temperature, max_length):
 def gradio_app():
     with gr.Blocks() as demo:
         gr.Markdown(title)
-        prompt = gr.Textbox(label="WordPhrases", value=examplecofee, lines=5)
-        custom_prompt = gr.Textbox(label="Title", value="Cortado", lines=1)
+        custom_prompt = gr.Textbox(label="WordPhrases", value=examplecofee, lines=5)
+        prompt = gr.Textbox(label="Title", value="Cortado", lines=1)
         with gr.Row():
             temperature = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, value=0.5, label="Temperature")
             max_length = gr.Slider(minimum=250, maximum=1024, step=10, value=450, label="Generate Length")