lxianl455

If I want to create a new dataset (not CNN/DailyMail and XSum) , what should I prepare for it?

1

I noticed that the unprocessed data should be like the following format:  If I want to create a new dataset (not CNN/DailyMail and XSum) , what should I prepare...

Blip2 Help! When trying the run_scripts/blip2/train/train_caption_coco.sh

1

When i try run_scripts/blip2/train/train_caption_coco.sh, it turn out to be an error: ` File "/home/jovyan/environment/anaconda3/body/envs/lavis/lib/python3.8/os.py", line 223, in makedirs mkdir(name, mode) PermissionError: [Errno 13] Permission denied: '/export'` I did not find...

Effect of the text_threshold and box_threshold

1

Waht is the effect of the text_threshold and box_threshold?

SAM predictor Error

3

When I try to get a mask, I got an error: Traceback (most recent call last): File "grounded_sam_demo.py", line 206, in masks, _, _ = predictor.predict_torch( File "/data0/lxl/environment/anaconda3_22_5_11/envs/try_segment/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27,...

apply an entire BERT as text encoder

1

Can I apply an entire BERT as text encoder ? Not just 6 layer. What should I do to apply an entire BERT as text encoder ? And another BERT...

About the newly release checkpoint.

12

  Is the bin file in the figure the pre-trained checkpoint?

ImportError fastNLP

1

我运行sh 15_pretrain_full.sh，但是出现以下错误 `7e-5 Traceback (most recent call last): File "MAESC_training.py", line 19, in from src.model.MAESC_model import MultiModalBartModel_AESC File "/home/jovyan/multimodal_aspect_sentiment/VLP-MABSA/src/model/MAESC_model.py", line 2, in from fastNLP.modules import Seq2SeqEncoder, Seq2SeqDecoder, State ImportError: cannot...

Error

2

I just try: import wikipedia print(wikipedia.summary("google", sentences=1)) but i got the follow error: raise PageError(self.title) wikipedia.exceptions.PageError: Page id "google\" does not match any pages. Try another id! What should i...

data

1

When i run this command `python main.py --base configs/multi30k/vqgan_c128_l6.yaml --train True --gpus 1,2` Error occurs : `FileNotFoundError: [Errno 2] No such file or directory: 'data/multi30k/full_train.txt'` But i did not find...

预训练数据集问题

1

请问使用的预训练数据集是什么？ 我去BELLE仓库去看，看到的大多数都是指令微调的数据集。你是使用类似于[Multiturn Chat](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)这种数据集去做预训练的吗？