Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-30 06:00:15 +01:00
Code Issues Packages Projects Releases Wiki Activity

Remove obsolete pre_layer parameter

Browse Source
This commit is contained in:
oobabooga 2024-06-12 18:56:44 -07:00
parent 46174a2d33
commit 2d196ed2fe
3 changed files with 1 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
modules/models_settings.py
View File

@ -204,14 +204,11 @@ def update_model_parameters(state, initial=False):
value = vars(shared.args_defaults)[element]
# Making some simple conversions
if element in ['wbits', 'groupsize', 'pre_layer']:
if element in ['wbits', 'groupsize']:
value = int(value)
elif element == 'cpu_memory' and value is not None:
value = f"{value}MiB"
if element in ['pre_layer']:
value = [value] if value > 0 else None
setattr(shared.args, element, value)
found_positive = False

1
modules/ui.py
View File

@ -70,7 +70,6 @@ def list_model_elements():
'use_double_quant',
'wbits',
'groupsize',
'pre_layer',
'triton',
'desc_act',
'no_inject_fused_attention',

1
modules/ui_model_menu.py
View File

@ -101,7 +101,6 @@ def create_ui():
shared.gradio['threads_batch'] = gr.Slider(label="threads_batch", minimum=0, step=1, maximum=256, value=shared.args.threads_batch)
shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=shared.args.wbits if shared.args.wbits > 0 else "None")
shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=shared.args.groupsize if shared.args.groupsize > 0 else "None")
shared.gradio['pre_layer'] = gr.Slider(label="pre_layer", minimum=0, maximum=100, value=shared.args.pre_layer[0] if shared.args.pre_layer is not None else 0)
shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7')
shared.gradio['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=0, maximum=shared.settings['truncation_length_max'], step=256, info='Context length. Try lowering this if you run out of memory while loading the model.', value=shared.args.max_seq_len)
with gr.Blocks():