Update app.py

app.py

@@ -3,9 +3,12 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
 # Load the model and tokenizer
-model_name = "medgpt"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("valeriojob/MedGPT-Llama3.1-8B-BA-v.1")
+model = AutoModelForCausalLM.from_pretrained("valeriojob/MedGPT-Llama3.1-8B-BA-v.1")
 
 def respond_to_query(user_input):
     input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")