4.2. Deploying Gradio Demo -- code bug -- KeyError: 'mode'

[yj77-enen]

我首先按照 #4.1 去下载模型，放在指定的目录下：
imagebind_huge.pth放在[[./ckpt/pretrained_ckpt/imagebind_ckpt/huge]]
vicuna-7b-delta-v0放在 [[./ckpt/pretrained_ckpt/vicuna_ckpt/]]
nextgpt_7b_tiva_v0 放在[[./ckpt/delta_ckpt/nextgpt/7b_tiva_v0]]
然后按照 #4.2 执行scripts/app.sh脚本的时候报错了

4.2. Deploying Gradio Demo
Upon completion of the checkpoint loading, you can run the demo locally via:

cd ./code
bash scripts/app.sh

=======================================

报错信息如下：
(nextgpt) [root@311 multimodel]# cd NExT-GPT/
(nextgpt) [root@311 NExT-GPT]# ls
ckpt code data figures LICENSE.md README.md requirements.txt
(nextgpt) [root@311 NExT-GPT]# cd code
(nextgpt) [root@311 code]# bash scripts/app.sh
Setting ds_accelerator to cuda (auto detect)
/root/miniconda3/envs/nextgpt/lib/python3.8/site-packages/torchvision/transforms/_functional_video.py:6: UserWarning: The 'torchvision.transforms._functional_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms.functional' module instead.
warnings.warn(
/root/miniconda3/envs/nextgpt/lib/python3.8/site-packages/torchvision/transforms/_transforms_video.py:22: UserWarning: The 'torchvision.transforms._transforms_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms' module instead.
warnings.warn(
/data/ivb/multimodel/NExT-GPT/code/model/custom_sd.py:28: FutureWarning: Importing DiffusionPipeline or ImagePipelineOutput from diffusers.pipeline_utils is deprecated. Please import from diffusers.pipelines.pipeline_utils instead.
from diffusers.pipeline_utils import DiffusionPipeline
[!] load base configuration: config/base.yaml
Traceback (most recent call last):
File "demo_app.py", line 27, in
args.update(load_config(args))
File "/data/ivb/multimodel/NExT-GPT/code/config/init.py", line 28, in load_config
stage_configuration = load_model_config(args['stage'], args['mode'])
KeyError: 'mode'

[kqcode]

@yj77-enen I think you can solve this problem by replacing 'mode' with 'model'.