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

Minor deletion

Browse source
This commit is contained in:
oobabooga 2023-04-21 12:41:27 -03:00
parent d46b9b7c50
commit eddd016449
1 changed files with 0 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -123,7 +123,6 @@ parser.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized m
parser.add_argument('--model_type', type=str, help='Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.')
parser.add_argument('--groupsize', type=int, default=-1, help='Group size.')
parser.add_argument('--pre_layer', type=int, default=0, help='The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models.')
parser.add_argument('--file-path', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
parser.add_argument('--monkey-patch', action='store_true', help='Apply the monkey patch for using LoRAs with quantized models.')
parser.add_argument('--no-quant_attn', action='store_true', help='(triton) Disable quant attention. If you encounter incoherent results try disabling this.')
parser.add_argument('--no-warmup_autotune', action='store_true', help='(triton) Disable warmup autotune.')