From 413198c8dcd7e9872f34eafef97ae55e54dcc57b Mon Sep 17 00:00:00 2001 From: Nikita Savelyev Date: Mon, 9 Dec 2024 09:45:19 +0100 Subject: [PATCH] Update backup-precision option description --- docs/source/openvino/export.mdx | 4 ++-- optimum/commands/export/openvino.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/source/openvino/export.mdx b/docs/source/openvino/export.mdx index dd542be735..4876885219 100644 --- a/docs/source/openvino/export.mdx +++ b/docs/source/openvino/export.mdx @@ -84,8 +84,8 @@ Optional arguments: The group size to use for quantization. Recommended value is 128 and -1 uses per-column quantization. --backup-precision {none,int8_sym,int8_asym} - Defines a backup precision for mixed-precision weight compression. Only valid for int4 weight - format. If not provided, backup precision is int8_asym. 'none' stands for original floating- + Defines a backup precision for mixed-precision weight compression. Only valid for 4-bit weight + formats. If not provided, backup precision is int8_asym. 'none' stands for original floating- point precision of the model weights, in this case weights are retained in their original precision without any quantization. 'int8_sym' stands for 8-bit integer symmetric quantization without zero point. 'int8_asym' stands for 8-bit integer asymmetric quantization with zero diff --git a/optimum/commands/export/openvino.py b/optimum/commands/export/openvino.py index 5e951aa438..cfc001d87f 100644 --- a/optimum/commands/export/openvino.py +++ b/optimum/commands/export/openvino.py @@ -123,7 +123,7 @@ def parse_args_openvino(parser: "ArgumentParser"): choices=["none", "int8_sym", "int8_asym"], default=None, help=( - "Defines a backup precision for mixed-precision weight compression. Only valid for int4 weight format. " + "Defines a backup precision for mixed-precision weight compression. Only valid for 4-bit weight formats. " "If not provided, backup precision is int8_asym. 'none' stands for original floating-point precision of " "the model weights, in this case weights are retained in their original precision without any " "quantization. 'int8_sym' stands for 8-bit integer symmetric quantization without zero point. 'int8_asym' "