Ruo Zhang

gpu memory not realesed

4

Hi @wenbowen123, thank you for your nice work. I've been trying to run Bundletrack on a collections of video clips. To automatically swith between each clips, I simply declare Bundler...

Hi, @xavierpuigf Thank you for your excellent work. I am trying to use the two datasets _ActivityProgram_ and _VirtualHome Activity_ mentioned in the paper https://arxiv.org/pdf/1806.07011.pdf. I have downloaded the two...

Dear @huangwl18, Thank you for your excellent work. I have a small question regarding the dataset you used in your research. I noticed that the dataset you used contains around...

How to evaluate InternVL-Chat-V1-5 on video benchmark

1

Hi @czczup, Thanks for open-sourcing such a wonderful job. The amazing performance on video task is surprising. Just a quesiton about how to evaluate the intervl-chat-v1-5 on video benchmark such...

Finetune script for trainning internvl2-76B

1

@czczup Thank you so much for providing the finetune script for Internvl2. Do you have any plan to release the finetune code for internvl2-76B model?

Evaluation of the video detailed description

1

Hi @ZhangYuanhan-AI Thanks for the wonderful job. Just a question about the evaluation of the detailed description. I found the result of the gpt eval score will be convert to...

Difference between MMBench_DEV and MMBench_Test

1

HI, @kennymckormick Thanks for open-sourcing such a wonderful job. As I can not find the score of the MMBench_DEV, would you mind to tell me what's the difference between the...

[BUG] <title> 请问在用deepspeed zero3 训练的过程因为minicpm navit的逻辑会导致不同rank上的image feature size 不同这样会hang住，这个是怎么解决的？zero2是没有问题的

3

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...