AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-01 01:26:03 -04:00
Code Issues Packages Projects Releases Wiki Activity

Move the import to the top

Browse Source
This commit is contained in:
oobabooga 2023-03-10 10:51:12 -03:00
parent 9fbd60bf22
commit e461c0b7a0
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
modules/models.py
View File

@ -112,12 +112,13 @@ def load_model(model_name):
model = load_quant(path_to_model, Path(f"models/{pt_model}"), 4) model = load_quant(path_to_model, Path(f"models/{pt_model}"), 4)
if shared.args.gpu_memory: if shared.args.gpu_memory:
import accelerate
max_memory = {} max_memory = {}
for i in range(len(shared.args.gpu_memory)): for i in range(len(shared.args.gpu_memory)):
max_memory[i] = f"{shared.args.gpu_memory[i]}GiB" max_memory[i] = f"{shared.args.gpu_memory[i]}GiB"
max_memory['cpu'] = f"{shared.args.cpu_memory or '99'}GiB" max_memory['cpu'] = f"{shared.args.cpu_memory or '99'}GiB"
import accelerate
device_map = accelerate.infer_auto_device_map(model, max_memory=max_memory, no_split_module_classes=["LLaMADecoderLayer"]) device_map = accelerate.infer_auto_device_map(model, max_memory=max_memory, no_split_module_classes=["LLaMADecoderLayer"])
model = accelerate.dispatch_model(model, device_map=device_map) model = accelerate.dispatch_model(model, device_map=device_map)
else: else: