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

AutoGPTQ: Add --disable_exllamav2 flag (Mixtral CPU offloading needs this)

Browse source
This commit is contained in:
oobabooga 2023-12-15 06:46:13 -08:00
parent 7de10f4c8e
commit 3bbf6c601d
7 changed files with 16 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/ui_model_menu.py
View file

@ -125,6 +125,7 @@ def create_ui():
shared.gradio['logits_all'] = gr.Checkbox(label="logits_all", value=shared.args.logits_all, info='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.')
shared.gradio['use_flash_attention_2'] = gr.Checkbox(label="use_flash_attention_2", value=shared.args.use_flash_attention_2, info='Set use_flash_attention_2=True while loading the model.')
shared.gradio['disable_exllama'] = gr.Checkbox(label="disable_exllama", value=shared.args.disable_exllama, info='Disable ExLlama kernel.')
shared.gradio['disable_exllamav2'] = gr.Checkbox(label="disable_exllamav2", value=shared.args.disable_exllamav2, info='Disable ExLlamav2 kernel.')
shared.gradio['no_flash_attn'] = gr.Checkbox(label="no_flash_attn", value=shared.args.no_flash_attn, info='Force flash-attention to not be used.')
shared.gradio['cache_8bit'] = gr.Checkbox(label="cache_8bit", value=shared.args.cache_8bit, info='Use 8-bit cache to save VRAM.')
shared.gradio['no_use_fast'] = gr.Checkbox(label="no_use_fast", value=shared.args.no_use_fast, info='Set use_fast=False while loading the tokenizer.')