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

Remove GGML support

Browse source
This commit is contained in:
oobabooga 2023-09-11 07:30:56 -07:00
parent cc7b7ba153
commit ed86878f02
15 changed files with 24 additions and 123 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -126,8 +126,6 @@ parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layer
parser.add_argument('--tensor_split', type=str, default=None, help="Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17")
parser.add_argument('--n_ctx', type=int, default=2048, help='Size of the prompt context.')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='Seed for llama-cpp models. Default 0 (random)')
parser.add_argument('--n_gqa', type=int, default=0, help='grouped-query attention. Must be 8 for llama-2 70b.')
parser.add_argument('--rms_norm_eps', type=float, default=0, help='5e-6 is a good value for llama-2 models.')
# GPTQ
parser.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')