Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 08:07:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

Fix flash-attn UI parameter to actually store true. (#6076)

Browse Source
This commit is contained in:
Forkoz 2024-06-13 03:34:54 +00:00 committed by GitHub
parent 3abafee696
commit 1d79aa67cf
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
modules/loaders.py
View File

@ -46,7 +46,7 @@ loaders_and_params = OrderedDict({
'no_offload_kqv', 'no_offload_kqv',
'row_split', 'row_split',
'tensorcores', 'tensorcores',
'flash-attn', 'flash_attn',
'streaming_llm', 'streaming_llm',
'attention_sink_size', 'attention_sink_size',
], ],
@ -72,7 +72,7 @@ loaders_and_params = OrderedDict({
'no_offload_kqv', 'no_offload_kqv',
'row_split', 'row_split',
'tensorcores', 'tensorcores',
'flash-attn', 'flash_attn',
'streaming_llm', 'streaming_llm',
'attention_sink_size', 'attention_sink_size',
'llamacpp_HF_info', 'llamacpp_HF_info',

2
modules/ui.py
View File

@ -102,7 +102,7 @@ def list_model_elements():
'no_offload_kqv', 'no_offload_kqv',
'row_split', 'row_split',
'tensorcores', 'tensorcores',
'flash-attn', 'flash_attn',
'streaming_llm', 'streaming_llm',
'attention_sink_size', 'attention_sink_size',
'hqq_backend', 'hqq_backend',

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['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.')
shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming_llm", value=shared.args.streaming_llm, info='(experimental) Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.') shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming_llm", value=shared.args.streaming_llm, info='(experimental) Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')