MeloZhang

a big gap between the pdb results from openfold and alphafold2 (colab)

4

Hi! After running openfold according to the default configuration, I found that there was a big difference between the output pdb file of openfold and alphafold (colab version). After comparing...

Hello, I encountered some file format issues while training the model.Now I have a batch of my own Clues and Answers data that I want to use for training, but...

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

4

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。  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？