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

Remove --sdp-attention, --xformers flags (#5126)

Browse source
This commit is contained in:
oobabooga 2023-12-31 01:36:51 -03:00 • committed by GitHub
parent b7dd1f9542
commit 8e397915c9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 1 additions and 180 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -98,8 +98,6 @@ group.add_argument('--disk-cache-dir', type=str, default='cache', help='Director
group.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision (using bitsandbytes).')
group.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
group.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces VRAM usage slightly, but it comes at a performance cost.')
group.add_argument('--xformers', action='store_true', help='Use xformer\'s memory efficient attention. This is really old and probably doesn\'t do anything.')
group.add_argument('--sdp-attention', action='store_true', help='Use PyTorch 2.0\'s SDP attention. Same as above.')
group.add_argument('--trust-remote-code', action='store_true', help='Set trust_remote_code=True while loading the model. Necessary for some models.')
group.add_argument('--force-safetensors', action='store_true', help='Set use_safetensors=True while loading the model. This prevents arbitrary code execution.')
group.add_argument('--no_use_fast', action='store_true', help='Set use_fast=False while loading the tokenizer (it\'s True by default). Use this if you have any problems related to use_fast.')