Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 08:07:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add low vram mode on llama cpp (#3076)

Browse Source
This commit is contained in:
Gabriel Pena 2023-07-12 11:05:13 -03:00 committed by GitHub
parent 180420d2c9
commit eedb3bf023
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
modules/llamacpp_model.py
View File

@ -49,6 +49,7 @@ class LlamaCppModel:
'n_batch': shared.args.n_batch,
'use_mmap': not shared.args.no_mmap,
'use_mlock': shared.args.mlock,
'low_vram': shared.args.low_vram,
'n_gpu_layers': shared.args.n_gpu_layers
}

1
modules/loaders.py
View File

@ -34,6 +34,7 @@ loaders_and_params = {
'n_batch',
'threads',
'no_mmap',
'low_vram',
'mlock',
'llama_cpp_seed',
],

1
modules/shared.py
View File

@ -120,6 +120,7 @@ parser.add_argument('--use_double_quant', action='store_true', help='use_double_
parser.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
parser.add_argument('--n_batch', type=int, default=512, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
parser.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
parser.add_argument('--low-vram', action='store_true', help='Low VRAM Mode')
parser.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')

1
modules/ui.py
View File

@ -57,6 +57,7 @@ def list_model_elements():
'threads',
'n_batch',
'no_mmap',
'low_vram',
'mlock',
'n_gpu_layers',
'n_ctx',

1
server.py
View File

@ -248,6 +248,7 @@ def create_model_menus():
shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit)
shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant)
shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap)
shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram)
shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)
shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Make sure to inspect the .py files inside the model folder before loading it with this option enabled.')