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

Update documentation

Browse source
This commit is contained in:
oobabooga 2023-03-28 17:46:00 -03:00
parent 0bec15ebcd
commit 010b259dde
3 changed files with 2 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/GPTQ_loader.py
View file

@ -48,7 +48,6 @@ def _load_quant(model, checkpoint, wbits, groupsize=-1, faster_kernel=False, exc
return model
def load_quantized(model_name):
if not shared.args.model_type:
# Try to determine model type from model name

2
modules/shared.py
View file

@ -84,7 +84,7 @@ parser.add_argument('--gptq-bits', type=int, default=0, help='DEPRECATED: use --
parser.add_argument('--gptq-model-type', type=str, help='DEPRECATED: use --model_type instead.')
parser.add_argument('--gptq-pre-layer', type=int, default=0, help='DEPRECATED: use --pre_layer instead.')
parser.add_argument('--wbits', type=int, default=0, help='GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
parser.add_argument('--model_type', type=str, help='GPTQ: Model type of pre-quantized model. Currently only LLaMA and OPT are supported.')
parser.add_argument('--model_type', type=str, help='GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.')
parser.add_argument('--groupsize', type=int, default=-1, help='GPTQ: Group size.')
parser.add_argument('--pre_layer', type=int, default=0, help='GPTQ: The number of layers to preload.')