From e3fd2776a318a3a7b9d33315cc42c04c181f6d2f Mon Sep 17 00:00:00 2001
From: B-201 <116639249+B-201@users.noreply.github.com>
Date: Mon, 29 Apr 2024 19:23:04 +0800
Subject: [PATCH] Fix bug causing random initialization of bias when using GPTQ
 quantization with models without bias (#1827)

* Fix gptq quantization for models without bias

* Fix gptq quantization for models without bias
---
 optimum/gptq/quantizer.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/optimum/gptq/quantizer.py b/optimum/gptq/quantizer.py
index 289e3256825..2c2c9d7e71a 100644
--- a/optimum/gptq/quantizer.py
+++ b/optimum/gptq/quantizer.py
@@ -278,19 +278,20 @@ def _replace_by_quant_layers(self, module: nn.Module, names: List[str], name: st
                 elif isinstance(layer, Conv1D):
                     in_features = layer.weight.shape[0]
                     out_features = layer.weight.shape[1]
+                bias = layer.bias is not None
                 if not (self.desc_act) or self.group_size == -1:
                     new_layer = QuantLinear(
                         self.bits,
                         self.group_size,
                         in_features,
                         out_features,
-                        True,
+                        bias,
                         use_cuda_fp16=self.use_cuda_fp16,
                         weight_dtype=layer.weight.dtype,
                     )
                 else:
                     new_layer = QuantLinear(
-                        self.bits, self.group_size, in_features, out_features, True, weight_dtype=layer.weight.dtype
+                        self.bits, self.group_size, in_features, out_features, bias, weight_dtype=layer.weight.dtype
                     )
                 new_layer.device = device
                 setattr(module, attr, new_layer.to(device))