From 4f228717ad023182ffec98308893219a0415bda7 Mon Sep 17 00:00:00 2001 From: wenhuach21 Date: Tue, 29 Oct 2024 16:07:14 +0800 Subject: [PATCH] fix bug of backend (#294) --- README.md | 4 ++-- auto_round/backend.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index ca6abfa3..a7597134 100644 --- a/README.md +++ b/README.md @@ -57,14 +57,14 @@ pip install auto-round ### Basic Usage (Gaudi2/CPU/GPU) A user guide detailing the full list of supported arguments is provided by calling ```auto-round -h``` on the terminal. -Alternatively, you can use ```auto_round``` instead of ```auto-round```. +Alternatively, you can use ```auto_round``` instead of ```auto-round```. Set the format you want in `format` and multiple formats exporting has been supported. ```bash CUDA_VISIBLE_DEVICES=0 auto-round \ --model facebook/opt-125m \ --bits 4 \ --group_size 128 \ - --format auto_round \ + --format "auto_round,auto_gptq" \ --disable_eval \ --output_dir ./tmp_autoround ``` diff --git a/auto_round/backend.py b/auto_round/backend.py index ea79ac85..6afbf1ef 100644 --- a/auto_round/backend.py +++ b/auto_round/backend.py @@ -137,7 +137,7 @@ def feature_num_greater_checker(in_feature, out_feature, num): requirements=["intel-extension-for-transformers"]) BackendInfos['auto_round:qbits_zp'] = BackendInfo(device=["cpu"], sym=[True, False], - packing_format="qbits", + packing_format="qbits_zp+-1", bits=[2, 4, 8], group_size=None, priority=0 if "intel" in get_cpu_manufacturer() else 5, feature_checks=[],