mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Extend AutoGPTQ support for any GPTQ model (#1668)

Browse source
This commit is contained in:
LaaZa 2023-06-02 07:33:55 +03:00 • committed by GitHub
parent b4ad060c1f
commit 9c066601f5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 25 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -142,6 +142,7 @@ parser.add_argument('--fused_mlp', action='store_true', help='(triton) Enable fu
# AutoGPTQ
parser.add_argument('--autogptq', action='store_true', help='Use AutoGPTQ for loading quantized models instead of the internal GPTQ loader.')
parser.add_argument('--triton', action='store_true', help='Use triton.')
parser.add_argument('--desc_act', action='store_true', help='For models that don\'t have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.')
# FlexGen
parser.add_argument('--flexgen', action='store_true', help='Enable the use of FlexGen offloading.')