Update app.py

app.py

@@ -7,7 +7,7 @@ client = InferenceClient(
 
 
 def format_prompt(message, history):
-  prompt = "<s>"
+  prompt = "You are a helpful chatbot specialized in medical knowledge.\n"
   for user_prompt, bot_response in history:
     prompt += f"[INST] {user_prompt} [/INST]"
     prompt += f" {bot_response}</s> "
@@ -15,7 +15,7 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.9, max_length=2000, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -24,7 +24,7 @@ def generate(
 
     generate_kwargs = dict(
         temperature=temperature,
-        max_new_tokens=max_new_tokens,
+        max_length=max_length,
         top_p=top_p,
         repetition_penalty=repetition_penalty,
         do_sample=True,