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 2023-06-06 07:58:07 -03:00
parent d49d299b67
commit f06a1387f0
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server.py
View File

@ -377,13 +377,12 @@ def create_model_menus():
with gr.Box():
with gr.Row():
with gr.Column():
gr.Markdown('AutoGPTQ')
gr.Markdown('GPTQ')
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='\'desc_act\', \'wbits\', and \'groupsize\' are used for old models without a quantize_config.json.')
shared.gradio['gptq_for_llama'] = gr.Checkbox(label="gptq-for-llama", value=shared.args.gptq_for_llama, info='Use GPTQ-for-LLaMa loader instead of AutoGPTQ. pre_layer should be used for CPU offloading instead of gpu-memory.')
with gr.Column():
gr.Markdown('GPTQ-for-LLaMa')
shared.gradio['gptq_for_llama'] = gr.Checkbox(label="gptq-for-llama", value=shared.args.gptq_for_llama, info='Use GPTQ-for-LLaMa to load the GPTQ model instead of AutoGPTQ. pre_layer should be used for CPU offloading instead of gpu-memory.')
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")