Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 import torch
-model_name = "ruslanmv/Medical-Llama3-8B"
+model_name = "ruslanmv/Medical-Llama3-8B""
 device_map = 'auto'
 # Check if GPU is available
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -21,11 +21,11 @@ if device.type == "cuda":
         device_map=device_map
     )
 else:
-    model = AutoModelForCausalLM.from_pretrained(
-        model_name,
-        trust_remote_code=True,
-        use_cache=False
-    )
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+
+ # Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 tokenizer.pad_token = tokenizer.eos_token