brandonj60

For api-stream, you can hit the fn of the load_character function (I think it's 38?) and pass it data (character, name1, name2).

That's just how the system works. Your GPU likely doesn't have enough VRAM for both storing the model weights, and running inference against a full context. As your conversation grows,...

> Edit: Here is the file and line you need to modify: https://github.com/oobabooga/text-generation-webui/blob/main/modules/shared.py#L39 > Set it initially to something like 300 and test chatting for a bit to see if...

Print out max_length at line 33 of chat.py. You're saying it always says 2048, regardless of the UI slider?

> I looked around and there doesn't seem to be a way to force a part of the UI to update via a function, best I could find is a...