From cb2778f010d461e46da0fea37d7dcb2578fcdb6e Mon Sep 17 00:00:00 2001 From: Marc Sun Date: Tue, 12 Dec 2023 20:00:00 +0100 Subject: [PATCH] fix --- src/transformers/utils/quantization_config.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/transformers/utils/quantization_config.py b/src/transformers/utils/quantization_config.py index 62cc42dc9f47c9..711c393c1b94fc 100644 --- a/src/transformers/utils/quantization_config.py +++ b/src/transformers/utils/quantization_config.py @@ -363,7 +363,7 @@ class GPTQConfig(QuantizationConfigMixin): model_seqlen (`int`, *optional*): The maximum sequence length that the model can take. block_name_to_quantize (`str`, *optional*): - The transformers block name to quantize. + The transformers block name to quantize. If None, we will infer the block name using common patterns (e.g. model.layers) module_name_preceding_first_block (`List[str]`, *optional*): The layers that are preceding the first Transformer block. batch_size (`int`, *optional*, defaults to 1):