From 1de8b17829e927cd5d6be2a9cdedf00cc819d181 Mon Sep 17 00:00:00 2001 From: "Wang, Chang" Date: Mon, 5 Aug 2024 12:27:19 +0800 Subject: [PATCH] Update modeling_auto.py Signed-off-by: Wang, Chang --- .../transformers/modeling/modeling_auto.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/intel_extension_for_transformers/transformers/modeling/modeling_auto.py b/intel_extension_for_transformers/transformers/modeling/modeling_auto.py index 47f8b1e7e60..63540e11a74 100644 --- a/intel_extension_for_transformers/transformers/modeling/modeling_auto.py +++ b/intel_extension_for_transformers/transformers/modeling/modeling_auto.py @@ -161,9 +161,7 @@ def build_woq_model(model, quantization_config): from neural_compressor.adaptor.torch_utils.util import set_module weight_dtype = quantization_config.weight_dtype for n, m in model.named_modules(): - print(n) if n in quantization_config.llm_int8_skip_modules: - # import pdb;pdb.set_trace(); continue if isinstance(m, torch.nn.Linear): zp = getattr(