Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-client = InferenceClient("Qwen/Qwen2.5-7B-Instruct-1M:") #change LLM
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") #change LLM
 
 def respond(message, history):
     messages = [{"role": "system", "content": "You are a friendly chatbot."}] #change personality
@@ -10,7 +10,7 @@ def respond(message, history):
     messages.append({"role": "user", "content": "message"})
     response = client.chat_completion(
         messages,
-        max_tokens=100 #change response length
+        max_tokens=1000 #change response length
     )
     return response['choices'][0]['message']['content'].strip()