-
Hi! Thanks for the great work.
I am working on the multi-model Vision-QA tasks using internvl_chat_llava model.
When evaluate the internvl_chat_llava model, an error occurs:
```
Traceback (mos…
dszpr updated
3 months ago
-
再请教一个问题,训练好的sat模型如何再两张GPU上加载并推理? 我目前只有A100(40G)的版本,有时推理会报内u才能溢出。
请问如何设置多GPU推理?
下面模型加载部分如何设置呢?谢谢
`# load model
model, model_args = AutoModel.from_pretrained(
args.from_pretra…
-
The category title header style update should cascade across all the Feature/Child screens in the app.
AC:
- Category page template is updated with the new home screen personalization UI, in this li…
-
```
The configure line used in current ubuntu and debian packages of ffmpeg-damnvid
makes the binary unredistributable:
./configure --enable-memalign-hack --enable-libxvid --enable-libx264
--enable…
-
The link of [info_vqa](https://opencompass.openxlab.space/utils/VLMEval/InfoVQA_TEST.tsv ) is unreachable.
the same as `DocVQA_TEST` `InfoVQA_VAL` `InfoVQA_TEST`
-
03/26/2024 19:23:18 - INFO - __main__ - load_from_pretrained: ./output/vast/pretrain_vast/ckpt/model_step_204994.pt
03/26/2024 19:23:18 - INFO - __main__ - Load from pretrained dir ./output/vast/…
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
开始训练ser模型时报错,求佬帮忙看看
- 系统环境/System Environment:Ubuntu 18.04.6
- 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Relate…
-
您好,非常感谢您的工作,我有一个问题想咨询您。请问如何在线评估CLEVR数据集的test.txt呢?是在这个网站上吗?[](https://eval.ai/web/challenges/list)我没有找到,您方便解答我的疑惑吗。 希望收到您的回复,谢谢。
-
What's the threshold did you use when evaluating VLM's harmness with Beaver-dam-7B?
-
Thank you for your contribution. I encountered the problem "FileNotFoundError: Couldn't find a dataset script at /cpfs01/shared/public/cl/datasets/OCR-VQA/OCR-VQA.py or any data file in the same direc…