Update app.py

app.py

@@ -4,8 +4,16 @@ import torch
 import gradio as gr
 import os
 import time
-model = AutoModelForCausalLM.from_pretrained("alibidaran/llama-2-7b-virtual_doctor-gguf",hf=True)
-tokenizer = AutoTokenizer.from_pretrained("alibidaran/llama-2-7b-virtual_doctor")
+model_id = "alibidaran/Gemma2_Virtual_doctor"
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
 def print_like_dislike(x: gr.LikeData):
     print(x.index, x.value, x.liked)