Update app.py
Browse files
app.py
CHANGED
@@ -14,6 +14,7 @@ dtype = torch.bfloat16
|
|
14 |
|
15 |
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
|
16 |
|
|
|
17 |
def load_model():
|
18 |
tokenizer = AutoTokenizer.from_pretrained(model_id, token=huggingface_token)
|
19 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
14 |
|
15 |
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
|
16 |
|
17 |
+
@spaces.GPU
|
18 |
def load_model():
|
19 |
tokenizer = AutoTokenizer.from_pretrained(model_id, token=huggingface_token)
|
20 |
model = AutoModelForCausalLM.from_pretrained(
|