Spaces:

satyaiyer
/

LLaMA3.2Instruct

Sleeping

satyaiyer commited on Apr 17

Commit

99d205d

verified ·

1 Parent(s): 83b7527

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -11,7 +11,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     quantization_config=bnb_config,
-    device_map="auto",
     use_auth_token=hf_token
 )

 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     quantization_config=bnb_config,
+    model.to("cpu"),
     use_auth_token=hf_token
 )