maxjeblick

Thanks for the clarification! As mentioned, the reason to not raise an `AssertionError` but rather a warning for system prompt missing is intentional. I'd go into the direction of adding...

> can we make this a GH action somehow? Let me check, should be doable

Thanks for opening this issue. It is already tracked [here](https://github.com/h2oai/h2o-llmstudio/issues/135), with this [PR](https://github.com/h2oai/h2o-llmstudio/pull/166) open to fix the issue.

Fixed by https://github.com/h2oai/h2o-llmstudio/pull/166

> Is that something that needs to be fixed? It's not a crucial bug, but probably easy to improve UX, i.e. automatically restrict to GPU ids available and also show...

> btw I also ran into this the other day and I was confused, so a fix would be good. Yeah, I planed to tackle it together with [this issue](https://github.com/h2oai/h2o-llmstudio/issues/190)....

That's a good suggestion, and certainly improves UX! Not sure what's the best way to add this, switching backbones would need to trigger an update of `ConfigNLPCausalLMTraining` parameters. Maybe add...

@psinger The potential UI implementation mentioned above will probably take some time and effort to work correctly. If it's ok with you, I'd merge this PR as is (or without...

Thank you for bringing up this issue! The occurrence of the `ValueError` can be attributed to selecting `float16` as the `Backbone Dtype`. This could be fixed by changing the data...

Like the idea! Tricky part may be progress bars (model downloads etc.) that could cause logging a new line at each update.