Update app.py

app.py

@@ -11,18 +11,16 @@ text_generation_pipeline = pipeline(
     "text-generation",
     model=model_name,
     model_kwargs={"torch_dtype": "auto", "load_in_4bit": True},
-    use_auth_token=hf_token
+    use_auth_token=hf_token  # Correctly placed for model and tokenizer loading
 )
 
 def generate_text(user_input):
     messages = [{"role": "user", "content": user_input}]
     prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    # Notice: No `use_auth_token` here. It's only needed when loading the model initially.
     outputs = text_generation_pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
     return outputs[0]["generated_text"]
 
-
-# Create the Gradio interface without the unsupported argument
+# Create the Gradio interface
 iface = gr.Interface(
     fn=generate_text,
     inputs=gr.Textbox(lines=2, placeholder="Type your question here..."),
@@ -31,6 +29,5 @@ iface = gr.Interface(
     description="A text generation model that understands your queries and generates concise, informative responses."
 )
 
-# Launch the interface with the share=True parameter to create a public link
-iface.launch(share=True)
-
+# Launch the interface (omit `share=True` when deploying on Hugging Face Spaces)
+iface.launch()