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 directory
FanshuoZeng opened this issue · 3 comments
FanshuoZeng commented
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 directory" while running the command "bash ./src/FastV/inference/eval/eval_ocrvqa_fastv_token_mask.sh". Could you please make this part of the file open source?
chenllliang commented
Thanks for your attention, you could replace the path to "howard-hou/OCR-VQA" , which has been uploaded to huggingface dataset. We would correct that in time.
FanshuoZeng commented
Thank you for your answer. Furthermore, I would like to know which is the implementation code of the FastV method described in the paper. Could you please tell me?
chenllliang commented
the implementation is here:
https://github.com/pkunlp-icler/FastV/blob/main/src/transformers/src/transformers/models/llama/modeling_llama.py#L730
Liang Chen
Peking University
…________________________________
发件人: zzzfffsss ***@***.***>
发送时间: Thursday, April 11, 2024 12:15:59 AM
收件人: pkunlp-icler/FastV ***@***.***>
抄送: Liang Chen ***@***.***>; Comment ***@***.***>
主题: Re: [pkunlp-icler/FastV] 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 directory (Issue #11)
Thank you for your answer. Furthermore, I would like to know which is the implementation code of the FastV method described in the paper. Could you please tell me?
―
Reply to this email directly, view it on GitHub<#11 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AKPQZIEUSVRKOVOJXFNGTCDY4VQT7AVCNFSM6AAAAABGAUYT3WVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANBXHE3TENBVGY>.
You are receiving this because you commented.Message ID: ***@***.***>