Update app.py

app.py

@@ -3,13 +3,16 @@ import gradio as gr
 
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
+def tokenize(text):
+    return tok.encode(text, add_special_tokens=False)
+    
 def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+    prompt = ""
+    for user_prompt, bot_response in history:
+        prompt += "<s>" + tokenize("[INST]") + tokenize(user_prompt) + tokenize("[/INST]")
+        prompt += tokenize(bot_response) + "</s> "
+    prompt += tokenize("[INST]") + tokenize(message) + tokenize("[/INST]")
+    return prompt
 
 def generate(
     prompt, history, temperature=0.2, max_new_tokens=512, top_p=0.95, repetition_penalty=1.0,