Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-21 23:57:58 +01:00
Code Issues Packages Projects Releases Wiki Activity

UI: mention that QuIP# does not work on Windows

Browse Source
This commit is contained in:
oobabooga 2023-12-18 18:05:02 -08:00
parent a23a004434
commit f6d701624c
2 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
modules/loaders.py
View File

@ -155,6 +155,7 @@ loaders_and_params = OrderedDict({
'trust_remote_code',
'no_use_fast',
'no_flash_attn',
'quipsharp_info',
],
'HQQ': [
'hqq_backend',

1
modules/ui_model_menu.py
View File

@ -102,6 +102,7 @@ def create_ui():
shared.gradio['alpha_value'] = gr.Slider(label='alpha_value', minimum=1, maximum=8, step=0.05, info='Positional embeddings alpha factor for NTK RoPE scaling. Recommended values (NTKv1): 1.75 for 1.5x context, 2.5 for 2x context. Use either this or compress_pos_emb, not both.', value=shared.args.alpha_value)
shared.gradio['rope_freq_base'] = gr.Slider(label='rope_freq_base', minimum=0, maximum=1000000, step=1000, info='If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63)', value=shared.args.rope_freq_base)
shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.', value=shared.args.compress_pos_emb)
shared.gradio['quipsharp_info'] = gr.Markdown('QuIP# only works on Linux.')
with gr.Column():
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)