mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-22 08:07:56 +01:00
Update GPTQ_Loader.py
Correcting decoder layer for renamed class.
This commit is contained in:
parent
ee164d1821
commit
53b6a66beb
@ -61,7 +61,7 @@ def load_quantized(model_name):
|
||||
max_memory[i] = f"{shared.args.gpu_memory[i]}GiB"
|
||||
max_memory['cpu'] = f"{shared.args.cpu_memory or '99'}GiB"
|
||||
|
||||
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)
|
||||
|
||||
# Single GPU
|
||||
|
Loading…
Reference in New Issue
Block a user