From db5f6cd1d8bd0a27a7318784157049218651470e Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sat, 30 Mar 2024 21:51:39 -0700
Subject: [PATCH] Fix ExLlamaV2 loaders using unnecessary "bits" metadata

---
 modules/models_settings.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/modules/models_settings.py b/modules/models_settings.py
index e487209e..b3d2dc64 100644
--- a/modules/models_settings.py
+++ b/modules/models_settings.py
@@ -89,7 +89,8 @@ def get_model_metadata(model):
                 if metadata['rope_scaling']['type'] == 'linear':
                     model_settings['compress_pos_emb'] = metadata['rope_scaling']['factor']
 
-            if 'quantization_config' in metadata:
+            # Read GPTQ metadata for old GPTQ loaders
+            if 'quantization_config' in metadata and metadata['quantization_config'].get('quant_method', '') != 'exl2':
                 if 'bits' in metadata['quantization_config']:
                     model_settings['wbits'] = metadata['quantization_config']['bits']
                 if 'group_size' in metadata['quantization_config']: