From f5e8f73a1ce540076e23d55060ad62618d2b8643 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Wed, 12 Jul 2023 08:38:17 +0200 Subject: [PATCH] Update server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py --- .../models/custom_modeling/flash_santacoder_modeling.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py b/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py index ff73e24f..a19623a5 100644 --- a/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py +++ b/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py @@ -81,8 +81,8 @@ def _load_multi_mqa_gptq( try: import os - bits = int(os.getenv("GTPQ_BITS")) - groupsize = int(os.getenv("GTPQ_GROUPSIZE")) + bits = int(os.getenv("GPTQ_BITS")) + groupsize = int(os.getenv("GPTQ_GROUPSIZE")) except Exception: raise e