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

Add low vram mode on llama cpp (#3076)

Browse source
This commit is contained in:
Gabriel Pena 2023-07-12 11:05:13 -03:00 • committed by GitHub
parent 180420d2c9
commit eedb3bf023
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
server.py
View file

@ -248,6 +248,7 @@ def create_model_menus():
shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit)
shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant)
shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap)
shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram)
shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)
shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Make sure to inspect the .py files inside the model folder before loading it with this option enabled.')