Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

AttributeError: 'str' object has no attribute 'requires_grad_'和config.json missing报错 #61

Open
Melo-1017 opened this issue Apr 6, 2024 · 5 comments

Comments

@Melo-1017
Copy link

我想了解一下vicuna的json中添加的pretrain_graph_model_path和graphgpt_stage1中的pretra_gnn是不是指同一个路径?也就是clip_gt_arxiv的路径?按照其他issue提到的做法,我在GraphGPT下直接新建了clip_gt_arxiv文件夹存放模型。
image
之后运行graphgpt_stage1,但还是提示 AttributeError: 'str' object has no attribute 'requires_grad_',此时我的命令是:

model_path=/root/nas/models_hf/vicuna-7b-v1.5
instruct_ds=/root/nas/GraphGPT/train_instruct_graphmatch.json
graph_data_path=/root/nas/GraphGPT/graphgpt/graph_data/graph_data_all.pt
pretra_gnn=/root/nas/GraphGPT/clip_gt_arxiv
output_model=/root/nas/GraphGPT/checkpoints/stage_1

vicuna中则是:"pretrain_graph_model_path": "/root/nas/GraphGPT/clip_gt_arxiv"
我若修改为pretra_gnn=clip_gt_arxiv,则报错config.json missing
请问我需要怎样配置模型路径来解决这个问题?

@HuizhaoWang
Copy link

可以在clip_gt_arxiv文件夹外再放置一个文件夹pretrained_gnn,然后设置设置.sh文件为pretra_gnn=clip_gt_arxiv,同时将下载vicuna模型中的config.json中的pretrain_graph_model_path参数设置为": "/root/nas/GraphGPT/pretrained_gnn/"

@zhuochunli
Copy link

可以在clip_gt_arxiv文件夹外再放置一个文件夹pretrained_gnn,然后设置设置.sh文件为pretra_gnn=clip_gt_arxiv,同时将下载vicuna模型中的config.json中的pretrain_graph_model_path参数设置为": "/root/nas/GraphGPT/pretrained_gnn/"

谢谢,解决了!

@msy0513
Copy link

msy0513 commented Jun 29, 2024

可以在clip_gt_arxiv文件夹外再放置一个文件夹pretrained_gnn,然后设置设置.sh文件为pretra_gnn=clip_gt_arxiv,同时将下载vicuna模型中的config.json中的pretrain_graph_model_path参数设置为": "/root/nas/GraphGPT/pretrained_gnn/"

请问这个新建的pretrained_gnn内需要放什么内容么?我按照你的说法改了之后,依然报错AssertionError: config.json missing

@zhuochunli
Copy link

可以在clip_gt_arxiv文件夹外再放置一个文件夹pretrained_gnn,然后设置设置.sh文件为pretra_gnn=clip_gt_arxiv,同时将下载vicuna模型中的config.json中的pretrain_graph_model_path参数设置为": "/root/nas/GraphGPT/pretrained_gnn/"

请问这个新建的pretrained_gnn内需要放什么内容么?我按照你的说法改了之后,依然报错AssertionError: config.json missing

不需要,就是GraphGPT/pretrained_gnn/clip_gt_arxiv, 然后clip_gt_arxiv里面包含clip_gt_arxiv_pub.pkl和config.json

@CigarOVO
Copy link

可以在clip_gt_arxiv文件夹外再放置一个文件夹pretrained_gnn,然后设置设置.sh文件为pretra_gnn=clip_gt_arxiv,同时将下载vicuna模型中的config.json中的pretrain_graph_model_path参数设置为": "/root/nas/GraphGPT/pretrained_gnn/"

请问这个新建的pretrained_gnn内需要放什么内容么?我按照你的说法改了之后,依然报错AssertionError: config.json missing

不需要,就是GraphGPT/pretrained_gnn/clip_gt_arxiv, 然后clip_gt_arxiv里面包含clip_gt_arxiv_pub.pkl和config.json

请问在运行graphgpt_eval.sh时,报错config.json missing,是需要修改stage_2中的config.json指向GraphGPT/pretrained_gnn/吗?我修改了还是报错

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants