InternVL

InternVL copied to clipboard

请问有在 V100-32G 的GPU上进行测试的finetune的脚本吗？

1

V100 不支持 flash-attn，想问下有没有不通过 flash-attn的脚本呢？以及用 internvl-v1.5 进行测试时，使用8卡还是报错 OOM的问题，请问怎么解决？迫切期待您的回复～

Qinger27

Is there a released mlp pretrained weights for internvl1.2 version

1

yucheng-ycz

請問可以在MacBook M系列的電腦上跑嗎？

5

如题。

seasoncool

Thanks for your great project. I noticed that the link for the zero-shot video classification task is not valid. is it not ready or just forget to link it?

simonnxren

Hi, I am trying out the single image - query and batch inference using int8 model. I have created a new environment following the installation instructions and trying out the...

gullalc

lighter internVL for contrastive use only

1

Hi, I am student working on joint embedding representation learning of text and image. I came accross your model and I am trying to load it and run it. However,...

mat10599

Unexpected output of InternVL 1.5 when using two images as input.

3

Hi, Thanks for your brilliant work! When I try to use two images as input and compare them, the model output unexpected results such as: 1. Based on your instructions,...

lbc12345

InternVL−Chat−V1.5-Int8的耗时是InternVL−Chat−V1.5的三倍吗？

1

InternVL−Chat−V1.5-Int8的耗时是InternVL−Chat−V1.5的三倍吗？我在A100上进行测试，同样的数据，InternVL−Chat−V1.5耗时550秒，InternVL−Chat−V1.5-Int8耗时1810秒

wtl0207

lexilii

Large 34B model OOM in evaluation

1

This line allocates the whole model onto GPU:0 again, should have used `device_map="auto"` when loading. https://github.com/OpenGVLab/InternVL/blob/2577068ba16fb3c17901fb3479a48b580c99c00b/internvl_chat/eval/mmmu/evaluate_mmmu.py#L286

kyleliang919