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

Revert "Bump llama-cpp-python to 0.2.18 (#4611)"

Browse source 
This reverts commit 923c8e25fb.
This commit is contained in:
oobabooga 2023-11-17 05:14:25 -08:00
parent e0a7cc5e0f
commit 9d6f79db74
17 changed files with 174 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -112,6 +112,7 @@ parser.add_argument('--no-mmap', action='store_true', help='Prevent mmap from be
parser.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')
parser.add_argument('--tensor_split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17.')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='Seed for llama-cpp models. Default is 0 (random).')
parser.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
parser.add_argument('--logits_all', action='store_true', help='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.')
parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
@ -181,7 +182,6 @@ parser.add_argument('--no-stream', action='store_true', help='DEPRECATED')
parser.add_argument('--mul_mat_q', action='store_true', help='DEPRECATED')
parser.add_argument('--api-blocking-port', type=int, default=5000, help='DEPRECATED')
parser.add_argument('--api-streaming-port', type=int, default=5005, help='DEPRECATED')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='DEPRECATED')
parser.add_argument('--use_fast', action='store_true', help='DEPRECATED')
args = parser.parse_args()