FP HAM

I use LORA all the time, You need to specify which loader are you using and what format of the model is. I see mentioned GPTQ - it still needs...

> Make sure to follow the instructions here: > > https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md#using-loras-in-4-bit-mode Does installing monkeypatch breaks the normal LORA training in 8-bit? I'm asking because I would love to experiment with...

> # Quick fix for llama3 doesn't stop correctly You need to also mention that this will break it for everything else than llama-3, otherwise some people would just blindly...

> @YakuzaSuske not everyone interacts on the same computer it's running on, I also use it on my phone, sometimes I'm curious and I'd rather not open terminal, ssh, find...

It's apparently not a bug but feature... go figure out https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/7965/commits/247a34498b337798a371d69483bbcab49b5c320c

This need to be somehow explained a bit better- no LLAMA I tried works with the current version - normal, 8 bit, all giving me the same error as here....

This has nothing to do with system prompt, system prompt is not part of the history where the chat_dialogue ends up.

``` 17:34:05-126060 ERROR Failed to load the model. Traceback (most recent call last): File "N:\text-generation-webui\modules\ui_model_menu.py", line 244, in load_model_wrapper shared.model, shared.tokenizer = load_model(selected_model, loader) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "N:\text-generation-webui\modules\models.py", line 93, in...

I made an extension that does this. Arbitrary set to max 3 loras, but works exactly as described https://github.com/FartyPants/sd-history-lora-slider