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

Add the --cpu option for llama.cpp to prevent CUDA from being used (#3432)

Browse source
This commit is contained in:
oobabooga 2023-08-03 11:00:36 -03:00 • committed by GitHub
parent 3e70bce576
commit 87dab03dc0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 40 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/shared.py
View file

@ -132,8 +132,8 @@ parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity.
parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')
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 llama2 70b.')
parser.add_argument('--rms_norm_eps', type=float, default=0, help='Must be 1e-5 for llama2 70b.')
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.')