Have cheaper mode

[whitead]

Perhaps using curie or sentence-transformer for embeddings (relatively cheap anyway). Distillbert might be good too.

https://huggingface.co/deepset/deberta-v3-large-squad2

[tiwentichat]

excuse me sir, i met a question on huggingface project you made.

Error like this:

This does not look like a text document: /tmp/requirementfyo6931m.txt. Path disable_check to ignore this error.

I draged a txt, input the apikey, then ask question below, the error came out.

actually, it's txt, why, what's wrong?

May you help me?

Thanks

[whitead]

@tiwentichat should be fixed

[liusok]

I also have this issue.

[liusok]

Hi, whitead. I got this message: "This model's maximum context length is 8191 tokens, however you requested 19149 tokens (19149 in your prompt; 0 for the completion). Please reduce your prompt; or completion length." I only ask a question with 10 words. How to fix it?

[tiwentichat]

@tiwentichat should be fixed

yes，great！

[whitead]

@liusok try latest version - had this problem too yesterday

[whitead]

Got cheaper mode now