Update app.py

app.py

@@ -1,9 +1,10 @@
 import gradio as gr
-from transformers import LlamaTokenizer, LlamaForCausalLM
 
-# Load the tokenizer and model
-tokenizer = LlamaTokenizer.from_pretrained("mailboxlab11/llama-3-medicalassistant")
-model = LlamaForCausalLM.from_pretrained("mailboxlab11/llama-3-medicalassistant")
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("mailboxlab11/llama-3-medicalassistant")
+model = AutoModelForCausalLM.from_pretrained("mailboxlab11/llama-3-medicalassistant")
 
 def generate(prompt):
     inputs = tokenizer(prompt, return_tensors="pt")