Yang Shi

icon indicating a website link https://dogneversleep.github.io icon indicating an email [email protected]

icon company Peking University icon location Beijing, China icon location 👨🏻‍🎓PhD student at Peking University | 🌠Interested in LLM / MLLM / AI Agent | 🐯 Life's a struggle.

Results 4 comments of Yang Shi

[Question] Cannot reproduce MME results on LLaVA-1.5-7B

@zjysteven Hi, did you solve it?

[Question] Cannot reproduce MME results on LLaVA-1.5-7B

> ### Question > Hi, I cannot reproduce MME results following [finetune.sh](https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/finetune.sh) on 665k instruction tuning dataset and evaluation scripts for MME. We followed all the settings except flash-attention on...

关于llava-v1.5-7b复现

@snowpine-max hi, did you solve it?

[Question] Cannot reproduce LLaVA-1.5-7b performance on MME with lmms-eval

> I also get the similar results:我也得到了类似的结果： > > same issue, please inform me if you solve it, thanks!!!