HKUDS / GraphGPT

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

https://arxiv.org/abs/2310.13023

HKUDS/GraphGPT Issues

Extract the Trained Projector
Closed 3 months ago7
How to evaluate the link prediction performance of GraphGPT
Closed a month ago2
GNN Baseline Too Low
Closed a month ago3
Issue in train_graph.py fail to load the model
Closed a month ago2
ERROR: Could not build wheels for mpi4py, Pillow, which is required to install pyproject.toml-based projects
Updated a month ago1
Some questions about input embedding of graph tokens
Closed a month ago3
out of memory
Updated a month ago1
graphgpt/train文件夹下不同的train_[*].py文件的作用？
Updated a month ago1
AttributeError: 'str' object has no attribute 'requires_grad_'和config.json missing报错
Updated 2 months ago1
AttributeError: 'GraphLlamaConfig' object has no attribute 'pretrain_graph_model_path'
Closed 2 months ago2
AttributeError: 'str' object has no attribute 'requires_grad_'
Closed 5 months ago7
关于graph matching
Updated 2 months ago
AssertionError: config.json missing
Closed 2 months ago1
No module named 'graphgpt'
Closed 2 months ago21
CUDA error: invalid device ordinal when running graphgpt_stage1.sh
Closed 2 months ago1
CUDA error: invalid device ordinal
Closed 2 months ago4
关于图编码器的问题
Closed 2 months ago1
The results of baselines are not reasonable and not correct (Clarified by author)
Closed 2 months ago13
Ask for the construction of datasets
Closed 2 months ago4
`graphgpt_stage1_lightning` 在第一个epoch训练结束后发生nccl超时错误。
Closed 2 months ago1
ModuleNotFoundError: No module named 'graphgpt'
Closed 3 months ago2
The error occurred while installing the packages listed in requirements.txt.
Closed 3 months ago2
A problem occurred when I tried to run stage1.sh
Closed 3 months ago4
I can not find this file: ./arxiv_ti_ab.json
Closed 3 months ago1
这个预训练模型可以用来做图结构的下游预测任务么？有相关示例么？
Closed 3 months ago1
How to calculate the Accuracy and Macro-f1 from the evaluation output?
Closed 5 months ago2
A question about training weights of embedding
Closed 3 months ago1
关于OOM错误
Closed 3 months ago3
hugging face访问不了，能不能加一个备选的访问链接
Closed 3 months ago2
CUDA out of memory.
Closed 3 months ago
Could this model used for other Graph Custom data Finetuning
Closed 5 months ago9
CUDA out of memory
Closed 5 months ago3
对比学习的一个细节问题
Closed 4 months ago2
About text feature
Closed 5 months ago2
bug in docs
Closed 5 months ago1
About baseline codes
Closed 5 months ago2
关于对比学习中的一些疑问
Closed 5 months ago8
> It is a very nice work and inspires me a lot. How do you evaluate the predictions generated from LLM? The paper claims that evaluating with Acc and F1. However it can be hard to evaluate the text sometimes.
Closed 5 months ago6
Performance of LLM baselines too low
Closed 6 months ago3
Requesting for the code for evaluation
Closed 6 months ago2
关于文本特征
Closed 5 months ago1
where is ./arxiv_ti_ab.json
Closed 7 months ago1
model.get_graph_tower().to(dtype=torch.float16, device=training_args.device) AttributeError: 'str' object has no attribute 'to'
Closed 6 months ago1
Why do you align GNN with a transformer training from scratch instead of LLaMA?
Closed 6 months ago2
Would you share your code for generating prompting files?
Closed 6 months ago4
Can the GraphGPT be used for LLM inference on other domain graph without retrainng?
Closed 6 months ago1
Would you provide the modified config.json of 'vicuna-7b-v1.5'?
Closed 6 months ago1
Error in Self-Supervised Instruction Tuning
Closed 6 months ago3
模型节点识别和关系推理能力
Closed 6 months ago2
Missing the code for structure-text grounding on many graphs
Closed 6 months ago1