Allow groupsize 1024, needed for larger models eg 30B to lower VRAM usage (#1660)

This commit is contained in:
Tom Jobbins 2023-05-02 04:46:26 +01:00 committed by GitHub
parent 78bd4d3a5c
commit 3c67fc0362
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -361,7 +361,7 @@ def create_model_menus():
with gr.Row(): with gr.Row():
with gr.Column(): with gr.Column():
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['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], value=shared.args.groupsize if shared.args.groupsize > 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")
with gr.Column(): with gr.Column():
shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "None") shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "None")