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

Bump llama-cpp-python to 0.2.11

Browse source
This commit is contained in:
jllllll 2023-10-01 18:08:10 -05:00
parent f2d82f731a
commit 41a2de96e5
No known key found for this signature in database
GPG key ID: 7FCD00C417935797
14 changed files with 25 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/llamacpp_hf.py
View file

@ -198,7 +198,6 @@ class LlamacppHF(PreTrainedModel):
'use_mmap': not shared.args.no_mmap,
'use_mlock': shared.args.mlock,
'mul_mat_q': shared.args.mul_mat_q,
'low_vram': shared.args.low_vram,
'numa': shared.args.numa,
'n_gpu_layers': shared.args.n_gpu_layers,
'rope_freq_base': RoPE.get_rope_freq_base(shared.args.alpha_value, shared.args.rope_freq_base),

1
modules/llamacpp_model.py
View file

@ -80,7 +80,6 @@ class LlamaCppModel:
'use_mmap': not shared.args.no_mmap,
'use_mlock': shared.args.mlock,
'mul_mat_q': shared.args.mul_mat_q,
'low_vram': shared.args.low_vram,
'numa': shared.args.numa,
'n_gpu_layers': shared.args.n_gpu_layers,
'rope_freq_base': RoPE.get_rope_freq_base(shared.args.alpha_value, shared.args.rope_freq_base),

2
modules/loaders.py
View file

@ -92,7 +92,6 @@ loaders_and_params = OrderedDict({
'n_batch',
'threads',
'no_mmap',
'low_vram',
'mlock',
'mul_mat_q',
'llama_cpp_seed',
@ -109,7 +108,6 @@ loaders_and_params = OrderedDict({
'n_batch',
'threads',
'no_mmap',
'low_vram',
'mlock',
'mul_mat_q',
'alpha_value',

1
modules/shared.py
View file

@ -117,7 +117,6 @@ 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('--mul_mat_q', action='store_true', help='Activate new mulmat kernels.')
parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')

1
modules/ui.py
View file

@ -71,7 +71,6 @@ def list_model_elements():
'threads',
'n_batch',
'no_mmap',
'low_vram',
'mlock',
'mul_mat_q',
'n_gpu_layers',

1
modules/ui_model_menu.py
View file

@ -107,7 +107,6 @@ def create_ui():
shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap)
shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
shared.gradio['numa'] = gr.Checkbox(label="numa", value=shared.args.numa, info='NUMA support can help on some systems with non-uniform memory access.')
shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram)
shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu)
shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)