Update app.py

app.py

@@ -4,7 +4,6 @@ from huggingface_hub import InferenceClient
 from sentence_transformers import SentenceTransformer
 import torch
 
-
 with open("knowledge.txt", "r", encoding="utf-8") as file:
   recent = file.read()
   # opens the text, saves as "file"
@@ -58,7 +57,10 @@ def get_top_chunks(query):
     # values of each index number is added to top_chunks
   return top_chunks
     
-client = InferenceClient('Qwen/Qwen2.5-72B-Instruct')
+client = InferenceClient(
+    model="Qwen/Qwen2.5-72B-Instruct",
+    token="your_token_here"
+)
 #client is where you can change the LLM model!
 def respond(message,history):
     if not message.strip():