From b7c627f9a0448b20667605d4583070aef1e68351 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sun, 25 Jun 2023 22:55:43 -0300 Subject: [PATCH] Set UI defaults --- server.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/server.py b/server.py index 455b6539..7a9cbf46 100644 --- a/server.py +++ b/server.py @@ -223,8 +223,8 @@ def create_model_menus(): shared.gradio['pre_layer'] = gr.Slider(label="pre_layer", minimum=0, maximum=100, value=shared.args.pre_layer[0] if shared.args.pre_layer is not None else 0) shared.gradio['autogptq_info'] = gr.Markdown('On some systems, AutoGPTQ can be 2x slower than GPTQ-for-LLaMa. You can manually select the GPTQ-for-LLaMa loader above.') shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7') - shared.gradio['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=2048, maximum=16384, step=256, info='Maximum sequence length.') - shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should typically be set to max_seq_len / 2048.') + shared.gradio['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=2048, maximum=16384, step=256, info='Maximum sequence length.', value=shared.args.max_seq_len) + shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should typically be set to max_seq_len / 2048.', value=shared.args.compress_pos_emb) with gr.Column(): shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)