diff --git a/modules/html_generator.py b/modules/html_generator.py index 902ffcc7..278f1632 100644 --- a/modules/html_generator.py +++ b/modules/html_generator.py @@ -1,8 +1,8 @@ +import functools import html import os import re import time -import functools from pathlib import Path import markdown diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py index 0e86a9f0..a31bbcf5 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -90,7 +90,7 @@ def create_ui(): shared.gradio['quant_type'] = gr.Dropdown(label="quant_type", choices=["nf4", "fp4"], value=shared.args.quant_type) shared.gradio['hqq_backend'] = gr.Dropdown(label="hqq_backend", choices=["PYTORCH", "PYTORCH_COMPILE", "ATEN"], value=shared.args.hqq_backend) - shared.gradio['n_gpu_layers'] = gr.Slider(label="n-gpu-layers", minimum=0, maximum=256, value=shared.args.n_gpu_layers, info='This must be set to more than 0 for your GPU to be used.') + shared.gradio['n_gpu_layers'] = gr.Slider(label="n-gpu-layers", minimum=0, maximum=256, value=shared.args.n_gpu_layers, info='Must be set to more than 0 for your GPU to be used.') shared.gradio['n_ctx'] = gr.Slider(minimum=0, maximum=shared.settings['truncation_length_max'], step=256, label="n_ctx", value=shared.args.n_ctx, info='Context length. Try lowering this if you run out of memory while loading the model.') shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='List of proportions to split the model across multiple GPUs. Example: 18,17') shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, step=1, value=shared.args.n_batch)