Update app.py

app.py

@@ -1,7 +1,10 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import pipeline
 
-client = InferenceClient(model="Simon0900/personalized-fitness-coach-JSON")
+pipe = pipeline(
+    "text-generation",
+    model="Simon0900/personalized-fitness-coach-JSON"
+)
 
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
@@ -13,13 +16,16 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
 
     prompt += f"User: {message}\nAssistant:"
 
-    return client.text_generation(
+    result = pipe(
         prompt,
         max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
+        do_sample=True
     )
 
+    return result[0]["generated_text"][len(prompt):]
+
 
 chatbot = gr.ChatInterface(
     respond,
@@ -34,5 +40,4 @@ chatbot = gr.ChatInterface(
 
 demo = chatbot
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()