rplescia
rplescia
> Update > > I downloaded and moved tokenizer.model file from base model Mistral 7B to the finetuned model directory. It seems to be converting. Will test it. > >...
So you've taken my idea and commercialised it... Not very nice when this is supposed to be an OPEN-SOURCE project!
This is totally not cool! At no point in this project's history has it been published that this project has a commercial angle to it until now. Now you take...
Thanks very much! I will download the latest nightly and test it!
> [@rplescia](https://github.com/rplescia) Hi, this feature has been launched in the agent settings. Feel free to try it. > > If your issue has been resolved, please feel free to close...
FYI - if you enter an API key and click OK it reports "modified" but nothing actually happens.
Hi, I can confirm this bug has been fixed in v0.10.0. Thanks!
Unfortunately, I cannot send the exact document because it is confidential, I will see if I can find a sample document that exhibits the same behaviour. The type of document...
@KevinHuSh If it is any help, the same error occurs when chucking the documents using 'One' and 'Manual' methods. I still haven't figured out what about the document can be...
I am reviewing legal documents like large loan agreements and contracts. I have spent much time trying different chunking methods, delimiters, token numbers, keywords etc. From what I can see...