Leonardo Silveira
Leonardo Silveira
i am facing similar issue, for some reason i count 10 tokens but the api says i am sending 18. if i send an empty payload (`payload = ""`), it...
@gitcyh @cryptoapebot this small project has one testcase sampling how i am using the prompt and showing the difference between local token counting and reported token counting. https://github.com/sombriks/aitokens i can...
@cryptoapebot so you mean there is nothing wrong with our approach of count tokens but we should take those extra tokens into account always? i could call them "margin tokens"...
@cryptoapebot that's the issue, by setting max_tokens we get the original error reported by @gitcyh . i have hope to be capable of count prompt tokens BEFORE submit them to...
Already tried, similar error.
the issue seems to be in the api itself: https://community.openai.com/t/tokenizer-and-playground-calculated-a-mismatch-between-the-number-of-tokens-and-the-bill-for-text-davinc-003/70624
@kartagis i`ve tried here with an android phone. the point is, you must provide the exact number the person used to join whatsapp. any number misplacement and it will fail...
the problem is gone on cordova-android 6.1.0, however i can't do any xhr request on this version. still pending to test if 6.1.0 alone is the problem or if 6.1.0...
also, i think this is the wrong place to open issues. crosswalk project uses this very unfriendly jira: https://crosswalk-project.org/jira/projects/XWALK/issues
so this is why vscode can hide kde window bar but not lapce? a gtk thing?