Update app.py

app.py

@@ -57,6 +57,12 @@ model = PeftModel.from_pretrained(model, "physician-ai/mistral-finetuned1",use_a
 tokenizer = AutoTokenizer.from_pretrained("physician-ai/mistral-finetuned1",use_auth_token=access_token)
 text_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=1024, temperature=0.8, top_p=0.95, repetition_penalty=1.15)
 
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+
 @spaces.GPU(duration=120)
 def chat_llama3_8b(message: str, 
               history: list,