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

Add settings UI for llama.cpp and fixed reloading of llama.cpp models (#2087)

Browse source
This commit is contained in:
Jakub Strnad 2023-05-16 00:51:23 +02:00 • committed by GitHub
parent 10869de0f4
commit 0227e738ed
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 18 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

15
server.py
View file

@ -360,7 +360,20 @@ def create_model_menus():
shared.gradio['download_model_button'] = gr.Button("Download")
with gr.Column():
shared.gradio['model_status'] = gr.Markdown('No model is loaded' if shared.model_name == 'None' else 'Ready')
with gr.Box():
gr.Markdown('llama.cpp parameters')
with gr.Row():
with gr.Column():
shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=32, value=shared.args.threads)
shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, value=shared.args.n_batch)
shared.gradio['n_gpu_layers'] = gr.Slider(label="n-gpu-layers", minimum=0, maximum=128, value=shared.args.n_gpu_layers)
with gr.Column():
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)
with gr.Row():
shared.gradio['model_status'] = gr.Markdown('No model is loaded' if shared.model_name == 'None' else 'Ready')
# In this event handler, the interface state is read and updated
# with the model defaults (if any), and then the model is loaded