We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
2 parents ee164d1 + 53b6a66 commit 4c13067Copy full SHA for 4c13067
modules/GPTQ_loader.py
@@ -61,7 +61,7 @@ def load_quantized(model_name):
61
max_memory[i] = f"{shared.args.gpu_memory[i]}GiB"
62
max_memory['cpu'] = f"{shared.args.cpu_memory or '99'}GiB"
63
64
- 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"])
65
model = accelerate.dispatch_model(model, device_map=device_map)
66
67
# Single GPU
0 commit comments