This commit is contained in:
Maya Eary 2023-03-28 20:43:50 +03:00
parent c8207d474f
commit 1c075d8d21

View file

@ -65,7 +65,7 @@ def load_quantized(model_name):
model_type = shared.args.model_type.lower() model_type = shared.args.model_type.lower()
if model_type == 'llama' and shared.args.pre_layer: if model_type == 'llama' and shared.args.pre_layer:
oad_quant = llama_inference_offload.load_quant load_quant = llama_inference_offload.load_quant
elif model_type in ('llama', 'opt', 'gptj'): elif model_type in ('llama', 'opt', 'gptj'):
load_quant = _load_quant load_quant = _load_quant
else: else: