From 09f807af83a608a78fc626bfe0bdad82d949f776 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sat, 21 Oct 2023 20:45:38 -0700
Subject: [PATCH] Use ExLlama_HF for GPTQ models by default

---
 modules/models_settings.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/models_settings.py b/modules/models_settings.py
index 1cf26902..de80fef9 100644
--- a/modules/models_settings.py
+++ b/modules/models_settings.py
@@ -110,7 +110,7 @@ def infer_loader(model_name, model_settings):
     if not path_to_model.exists():
         loader = None
     elif (path_to_model / 'quantize_config.json').exists() or ('wbits' in model_settings and type(model_settings['wbits']) is int and model_settings['wbits'] > 0):
-        loader = 'AutoGPTQ'
+        loader = 'ExLlama_HF'
     elif (path_to_model / 'quant_config.json').exists() or re.match(r'.*-awq', model_name.lower()):
         loader = 'AutoAWQ'
     elif len(list(path_to_model.glob('*.gguf'))) > 0: