From 53b6a66beb7520eb332642907eb6f82df28581ca Mon Sep 17 00:00:00 2001
From: askmyteapot <62238146+askmyteapot@users.noreply.github.com>
Date: Fri, 17 Mar 2023 18:34:13 +1000
Subject: [PATCH] Update GPTQ_Loader.py

Correcting decoder layer for renamed class.
---
 modules/GPTQ_loader.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/GPTQ_loader.py b/modules/GPTQ_loader.py
index c2723490bb..662182e73c 100644
--- a/modules/GPTQ_loader.py
+++ b/modules/GPTQ_loader.py
@@ -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