AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-19 15:56:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Lint

Browse Source
This commit is contained in:
oobabooga 2024-07-04 20:16:44 -07:00
parent a47de06088
commit 8b44d7b12a
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/models.py
View File

@ -147,7 +147,7 @@ def huggingface_loader(model_name):
params['force_safetensors'] = True params['force_safetensors'] = True
if shared.args.use_eager_attention: if shared.args.use_eager_attention:
params['attn_implementation'] = 'eager' params['attn_implementation'] = 'eager'
config = AutoConfig.from_pretrained(path_to_model, trust_remote_code=shared.args.trust_remote_code) config = AutoConfig.from_pretrained(path_to_model, trust_remote_code=shared.args.trust_remote_code)

2
modules/ui_model_menu.py
View File

@ -115,7 +115,7 @@ def create_ui():
shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit) 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['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant)
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['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['use_eager_attention'] = gr.Checkbox(label="use_eager_attention", value=shared.args.use_eager_attention, info='Set attn_implementation= eager while loading the model.') shared.gradio['use_eager_attention'] = gr.Checkbox(label="use_eager_attention", value=shared.args.use_eager_attention, info='Set attn_implementation= eager while loading the model.')
shared.gradio['flash_attn'] = gr.Checkbox(label="flash_attn", value=shared.args.flash_attn, info='Use flash-attention.') shared.gradio['flash_attn'] = gr.Checkbox(label="flash_attn", value=shared.args.flash_attn, info='Use flash-attention.')
shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices) shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices)
shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards.') shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards.')