Api only access

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Load model + tokenizer
 model_id = "MahiH/dialogpt-finetuned-chatbot"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id)
@@ -10,26 +9,21 @@ model.eval()
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 
-# Inference function
 def chat(prompt):
     input_text = f"Human: {prompt}\nAssistant: "
     input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
-
     with torch.no_grad():
         output_ids = model.generate(
             input_ids,
             max_new_tokens=100,
             do_sample=True,
-            top_k=50,
             top_p=0.95,
             temperature=0.8,
             pad_token_id=tokenizer.eos_token_id
         )
-    
-    response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
-    return response.split("Assistant:")[-1].strip()
-
-# Set up Gradio app (no UI, just API)
-app = gr.Interface(fn=chat, inputs=gr.Text(), outputs=gr.Text())
+    decoded = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    return decoded.split("Assistant:")[-1].strip()
 
-app.launch(share=True)
+# Setup API-only interface (UI will still be generated but ignored)
+demo = gr.Interface(fn=chat, inputs="text", outputs="text")
+demo.launch()  # DO NOT use share=True