when i try to load a csv file to my tuned model it gives me
"Failed to count tokens for this attachment." and "internal error"
Hello,
Thank you for contacting the Google Cloud Community.
I have gone through your reported issue, however it seems like this is an issue observed specifically at your end. It would need more specific debugging and analysis. To ensure a faster resolution and dedicated support for your issue, I kindly request you to file a support ticket by clicking here[1]. Our support team will prioritize your request and provide you with the assistance you need.
For individual support issues, it is best to utilize the support ticketing system. We appreciate your cooperation!
[1]: https://cloud.google.com/support/docs/manage-cases#creating_cases
Thanks for tour answer
It seems large pdf files more than 100k token aren't working anymore, I have tried smaller files it just work fine.
I have converted the pdf to docx file, there was no issue
I hope this helps to solve the issue
I have the same problem, Were you able to solve it or did they tell you why it happens?
I think the problem is the file extension, I tried with a book and that error came up, but when dividing the file into two smaller sections it let me, this considering that the entire book does not exceed the maximum amount of tokens by even close, I suppose it will be a bug
I have the same problem: "Failed to count tokens for this attachment."
when uploading multiple files
I am running into the same issue.
Same issue here and the file have already been used in the past with no problems
same here, its not working at all. only allowed me to upload 86K at once and i dnt know what limit is . seems like they have placed restriction upto how much you can upload at once. same error for me. the file used to upload just fine , but its not working anymore
when i try to load any pdf file it gives me
"Failed to count tokens for this attachment."
Same issue here. It is very frustrating as it deletes the files from existing prompt where I used the file before
This is happening to me, too (8/8/2024)
Idem. With PDFs that used to work fine.
This error also appeared in the documents I uploaded before, but there was no such error 5 weeks ago.
Cant believe this issue still exists after so many months, at least fix basic issues? Even simple CSV files of 100 MB have this issue, what is even the point of a long context LLM if it cant even work with smaller files?
User | Count |
---|---|
2 | |
2 | |
1 | |
1 | |
1 |