thu-ml/MMTrustEval

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)

PythonCC-BY-SA-4.0

Issues

Code for generating Adversarial examples (untargeted/targeted)
#6 opened a month ago by HashmatShadab
1
The channel to access the data seems to be closed
#5 opened 2 months ago by zhiyugege
1
Regarding testing my own model
#4 opened 2 months ago by ZixianGao
1
[BUG] LLava-RLHF run with BFloat16 failed
#3 opened 3 months ago by hxhcreate
1
Improve discoverability of your work on Hugging Face
#2 opened 3 months ago by NielsRogge
2
How to Replace Perceptive API？
#1 opened 3 months ago by hacker-jerry
1