CPU supported.

app.py

@@ -22,19 +22,11 @@ embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
 # ----------------------
 model_id = "BioMistral/BioMistral-7B"
 
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.float16,
-)
-
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 generation_model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.float16,
-    device_map="auto",
-    quantization_config=bnb_config
+    torch_dtype=torch.float32,
+    device_map={"": "cpu"}
 )
 
 # ----------------------