Do you also have this issue with Nemo?
After testing the model on cloud based 3090s/5090s, I've come to the conclusion that the upstream GPU implementation for this model is completely broken.
This didn't occur to me during testing as I don't own a GPU with 24 gb of vram myself, and as such did all the testing using slow CPU inference only.
I will look for an alternative 24 gb model, and add GLM-4 back in once it's properly implemented upstream.
I experimented with a system that generates custom items and crafting recipes from names, but it looks like Nemo isn't reliable enough to handle it properly.
The way NPCs generate custom items is by looking for a best match in the existing items and then adjusting its properties, which isn't sufficient for this purpose.
generating with the ai seems like it would be unreliable anyways as it may not work how it needs to or generate the wrong kind of item
so instead setting it up so the player can make their own items would be better via a similar system with custom characters you have already made. If it's not something you can do it's not a big deal.
I know damn well how hard something like this could be to set up so i wish you the best on that.
Thank you for making a fun game either way.