Sebastian Raschka
Sebastian Raschka
Thanks for the fix @casinca . And I also agree with you @d-kleine , the lines seem redundant and I removed them.
Thanks for the suggestions here, took me some time, but I am slowly catching up with some older items on my todo list. (I am trying to incorporate it via...
Thanks for the discussion and suggested improvements. > Hey it's giving an error that Pull request creation failed. Validation failed: must be a collaborator I think you may have accidentally...
I think you made the PR from a clone of the repo instead of a fork of the repo, which is probably why you are seeing that error.
Yes, Qwen models are really really good. They were among the best in the LLM Efficiency challenge last year. We never had time to add it, but I am in...
Good call @d-kleine . This was fixed in the book itself but I must have forgotten to fix it in the notes here.
Thanks for the comment. I think if it is all in upper case it, characters like ":-)" would become "":_)" etc. I think instead of doing `text.lower()`, which would catch...
You are totally right, thanks for the note! (cc @haydenliu )
> But there is one nuance 😊 We need to check for free disk space that is at least 2x of the model weight's size. The code first downloads weights...
RE CI failures: I actually now what happened here: the `transformer` package had a new release a few days back and this caused some issues with the rope unit tests...