From 7994b580d5c9fd4691276f40f7a9b6a204ce2564 Mon Sep 17 00:00:00 2001 From: Wojtek Kowaluk Date: Sat, 18 Mar 2023 02:27:26 +0100 Subject: [PATCH] clean up duplicated code --- modules/models.py | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/modules/models.py b/modules/models.py index c37b058..8fa7307 100644 --- a/modules/models.py +++ b/modules/models.py @@ -46,15 +46,17 @@ def load_model(model_name): if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.gptq_bits, shared.args.auto_devices, shared.args.disk, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None, shared.args.deepspeed, shared.args.flexgen, shared.is_RWKV]): if any(size in shared.model_name.lower() for size in ('13b', '20b', '30b')): model = AutoModelForCausalLM.from_pretrained(Path(f"models/{shared.model_name}"), device_map='auto', load_in_8bit=True) - if torch.has_mps: - model = AutoModelForCausalLM.from_pretrained( - Path(f"models/{shared.model_name}"),low_cpu_mem_usage=True, - torch_dtype=torch.bfloat16 if shared.args.bf16 else torch.float16 - ) - device = torch.device('mps') - model = model.to(device) else: - model = AutoModelForCausalLM.from_pretrained(Path(f"models/{shared.model_name}"), low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if shared.args.bf16 else torch.float16).cuda() + model = AutoModelForCausalLM.from_pretrained( + Path(f"models/{shared.model_name}"), + low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if shared.args.bf16 else torch.float16 + ) + if torch.has_mps: + device = torch.device('mps') + model = model.to(device) + else: + model = model.cuda() + # FlexGen elif shared.args.flexgen: