GraphGPT

GraphGPT copied to clipboard

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？

Melo-1017

Hello author, your work is excellent. How did you obtain feature embeddings for nodes in graph data? In the code, you provided this part directly, and I am curious about...

mubidiy

ModuleNotFoundError: No module named 'graphgpt'

1

When run the scripts/eval_script/graphgpt_eval.sh for evaluation, an error will occur: Traceback (most recent call last): File "./graphgpt/eval/run_graphgpt.py", line 7, in from graphgpt.conversation import conv_templates, SeparatorStyle ModuleNotFoundError: No module named 'graphgpt'...

zhuochunli

你好，我在使用[Jiabin99]发布的GraphGPT-7B-mix-all用作eval时遇到了报错，报错内容如下 ``` root@autodl-container-8cee4dbe08-5999a9bc:~/autodl-tmp/GraphGPT# bash graphgpt_eval.sh 2024-05-13 17:19:24,186 WARNING utils.py:585 -- Detecting docker specified CPUs. In previous versions of Ray, CPU detection in containers was incorrect. Please ensure that Ray has...

wlw-wlw

若不支持，请问该怎么调整代码模块呢？非常感谢！

fishfree

ERROR: Could not build wheels for mpi4py, Pillow, which is required to install pyproject.toml-based projects

1

I kept meeting this error message below in the environment installation step and i had also tried all the methods i found online. The Error Message is: ``` ERROR: Could...

HelloWorld4747

out of memory

3

在执行stag1.sh的时候，出现以下报错： ``` module._apply(fn) File "/root/miniconda3/envs/graphgpt/lib/python3.8/site-packages/torch/nn/modules/module.py", line 639, in _apply module._apply(fn) [Previous line repeated 2 more times] File "/root/miniconda3/envs/graphgpt/lib/python3.8/site-packages/torch/nn/modules/module.py", line 662, in _apply param_applied = fn(param) File "/root/miniconda3/envs/graphgpt/lib/python3.8/site-packages/torch/nn/modules/module.py", line 985, in...

xxrrnn

graphgpt/train文件夹下不同的train_[*].py文件的作用？

1

可以看到graphgpt/train文件夹下具有多个不同的train_[*].py： - train_graph.py - train_light.py - train_lora.py - train_mem.py 这些不同文件的作用是什么？

tigerbunny2023

您好，我想请问一下，当进行了graph和text的对齐后，为什么还需要graph matching呢？有点不太明白，这一步骤的作用。

zhuiyue233

When I run `sh ./scripts/tune_script/graphgpt_stage2.sh`, I encounter an error, and the error message is as follows: raise ValueError("Can't find a valid checkpoint at {resume_from_checkpoint}") ValueError: Can't find a valid checkpoint...

daixixiwang