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

Add --use_fast option (closes #3741)

Browse source
This commit is contained in:
oobabooga 2023-09-25 12:19:43 -07:00
parent b973b91d73
commit d0d221df49
6 changed files with 22 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -105,6 +105,7 @@ parser.add_argument('--no-cache', action='store_true', help='Set use_cache to Fa
parser.add_argument('--xformers', action='store_true', help="Use xformer's memory efficient attention. This should increase your tokens/s.")
parser.add_argument('--sdp-attention', action='store_true', help="Use torch 2.0's sdp attention.")
parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_remote_code=True while loading a model. Necessary for ChatGLM and Falcon.")
parser.add_argument('--use_fast', action='store_true', help="Set use_fast=True while loading a tokenizer.")
# Accelerate 4-bit
parser.add_argument('--load-in-4bit', action='store_true', help='Load the model with 4-bit precision (using bitsandbytes).')