Ted Sanders

Hard to say without seeing your data, but here a few suggestions: - Use a stop sequence (e.g., " END") in your fine-tuning completions so the model can signal a...

Can't help, unfortunately. Good luck in your experimentation.

Thanks for the contribution. Do you feel like this PR is in good shape? Would any particular review or feedback be useful? Will try to run things later this week,...

Looks great and happy to accept the contribution. Before merging, I think it might be helpful to add an introductory blurb at the top explaining what W&B is, and why...

Looks awesome. One tiny request - do you mind rewording 'other top ML teams' to just 'other ML teams'? Would love to keep things as inclusive and humble as possible,...

Merged. Thank you again!

Sorry for the trouble caused by type hinting. Most of the time this is caused by running a version of Python 3.7 or older. Deleting the the type hints should...

Sorry, I should have said Python 3.8 or older. Built in common types were added in 3.9. Hope you figured it out.

Unfortunately not. One option is to train a fine-tuned model to do that task, which won't need instructions.

Fine-tuned models are more expensive per token. If they allow you to use fewer tokens, they can be less expensive. It depends.