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

Add --checkpoint argument for GPTQ

Browse source
This commit is contained in:
oobabooga 2023-05-04 15:17:20 -03:00
parent dbddedca3f
commit b6ff138084
3 changed files with 8 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -131,6 +131,7 @@ 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('--checkpoint', type=str, help='The path to the quantized checkpoint file. If not specified, it will be automatically detected.')
parser.add_argument('--monkey-patch', action='store_true', help='Apply the monkey patch for using LoRAs with quantized models.')
parser.add_argument('--quant_attn', action='store_true', help='(triton) Enable quant attention.')
parser.add_argument('--warmup_autotune', action='store_true', help='(triton) Enable warmup autotune.')