Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-25 05:48:55 +01:00
Code Issues Packages Projects Releases Wiki Activity

Reorganize models tab

Browse Source
This commit is contained in:
oobabooga 2023-06-02 02:24:15 -03:00
parent d183c7d29e
commit 5a8162a46d
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
server.py
View File

@ -393,17 +393,18 @@ def create_model_menus():
with gr.Row():
with gr.Column():
gr.Markdown('GPTQ')
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['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "None")
with gr.Column():
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)
gr.Markdown('AutoGPTQ')
shared.gradio['autogptq'] = gr.Checkbox(label="autogptq", value=shared.args.autogptq, info='When enabled, gpu-memory should be used for CPU offloading instead of pre_layer.')
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
shared.gradio['desc_act'] = gr.Checkbox(label="desc_act", value=shared.args.desc_act, info='Only used for old models without a quantize_config.json.')
with gr.Column():
with gr.Row():
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['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "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)
with gr.Box():
gr.Markdown('llama.cpp')
with gr.Row():