Updating response parameters

app.py

@@ -4,8 +4,8 @@ from huggingface_hub import InferenceClient
 def chat_with_Zephyr(prompt, hugging_face_api_key):
     model_name = "HuggingFaceH4/zephyr-7b-beta"
     client = InferenceClient(model=model_name,token=hugging_face_api_key)
-    messages = [{"role": "user", "content": prompt}]
-    response = client.chat_completion(messages,max_tokens=50,temperature=0.7)
+    messages = [{"role": "user", "content": prompt+' Your response should be complete, and not end abruptly.'}]
+    response = client.chat_completion(messages,max_tokens=150,temperature=0.7)
     return response.choices[0].message.content
 
 demo = gr.Interface(fn=chat_with_Zephyr, inputs=[gr.Textbox(label="Prompt"),gr.Textbox(label="Hugging Face API Key", type="password")],outputs="text")