Deniss Abramovs

Oh wow! @wjentner you actually were right, i have re-enabled above mentioned toolkit and after downgrade, it finished without problems and all pods are up and running now!

Good that i have captured both logs @shivamerla , adding those below. These logs are from failing toolkit: https://gist.github.com/denissabramovs/0c3ad150ea2b9450a91b430a91704d08 These from successful toolkit: https://gist.github.com/denissabramovs/343c8fb0169866133fa1cc35b9d5365c Hope this helps to find the...

If you won't be able to reproduce, please ping me and i'll try to reproduce it locally again. Then we could catch that issue and possibly make some patch together....

Would be awesome to have Vicuna on-board in langchain integrations list.

ugh, so this have not been integrated?

Was surprised that there is no such setting by default in the --help, is it implemented or is considered out of scope for this project?

Stop token, generative model should be stopped when generation encounters stop token. I haven't found that in the cli. I suppose you have it built-in for each supported model.

ok, i checked your code, and i guess i got it. Had to add branch via @ in the url. this topic is closed

Actually, i see that subdirectory is not correctly extracted from the provided url. Your code is expecting it to be provided from another source.

``` vcs_parts = vcs_part.rsplit("@", 1) print(vcs_parts) entry["ref"] = vcs_parts[1].split("#", 1)[0].strip() entry[vcs] = vcs_parts[0].strip() # Check and extract subdirectory fragment if package.link.subdirectory_fragment: entry["subdirectory"] = package.link.subdirectory_fragment break ```