oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 07:03:37 +00:00
Code Issues Projects Releases Packages Wiki Activity

Fix several typos

Browse source
This commit is contained in:
oobabooga 2026-03-17 11:11:12 -07:00
parent 249861b65d
commit 2d141b54c5
5 changed files with 19 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -101,7 +101,7 @@ group.add_argument('--tensor-split', type=str, default=None, help='Split the mod
group.add_argument('--row-split', action='store_true', help='Split the model by rows across GPUs. This may improve multi-gpu performance.')
group.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
group.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
group.add_argument('--no-kv-offload', action='store_true', help='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')
group.add_argument('--no-kv-offload', action='store_true', help='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces performance.')
group.add_argument('--batch-size', type=int, default=1024, help='Maximum number of prompt tokens to batch together when calling llama-server. This is the application level batch size.')
group.add_argument('--ubatch-size', type=int, default=1024, help='Maximum number of prompt tokens to batch together when calling llama-server. This is the max physical batch size for computation (device level).')
group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')

6
modules/ui_model_menu.py
View file

@ -107,7 +107,7 @@ def create_ui():
shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu, info='Use PyTorch in CPU mode.')
shared.gradio['disk'] = gr.Checkbox(label="disk", value=shared.args.disk)
shared.gradio['row_split'] = gr.Checkbox(label="row_split", value=shared.args.row_split, info='Split the model by rows across GPUs. This may improve multi-gpu performance.')
shared.gradio['no_kv_offload'] = gr.Checkbox(label="no_kv_offload", value=shared.args.no_kv_offload, info='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')
shared.gradio['no_kv_offload'] = gr.Checkbox(label="no_kv_offload", value=shared.args.no_kv_offload, info='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces performance.')
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.')
@ -134,7 +134,7 @@ def create_ui():
ui.create_refresh_button(shared.gradio['customized_template'], lambda: None, lambda: {'choices': utils.get_available_instruction_templates()}, 'refresh-button', interactive=not mu)
shared.gradio['customized_template_submit'] = gr.Button("Submit", variant="primary", interactive=not mu)
gr.Markdown("This allows you to set a customized template for the model currently selected in the \"Model loader\" menu. Whenever the model gets loaded, this template will be used in place of the template specified in the model's medatada, which sometimes is wrong.")
gr.Markdown("This allows you to set a customized template for the model currently selected in the \"Model loader\" menu. Whenever the model gets loaded, this template will be used in place of the template specified in the model's metadata, which sometimes is wrong.")
with gr.Row():
shared.gradio['model_status'] = gr.Markdown('No model is loaded' if shared.model_name == 'None' else 'Ready')
@ -231,7 +231,7 @@ def load_model_wrapper(selected_model, loader, autoload=False):
def load_lora_wrapper(selected_loras):
yield ("Applying the following LoRAs to {}:\n\n{}".format(shared.model_name, '\n'.join(selected_loras)))
add_lora_to_model(selected_loras)
yield ("Successfuly applied the LoRAs")
yield ("Successfully applied the LoRAs")
def download_model_wrapper(repo_id, specific_file, progress=gr.Progress(), return_links=False, check=False):