XaiJu
Multiic
Multiic

patreon


0.3.77: local model

✨ integrated koboldcpp with local model*
✨ desktop: added welcome screen with choice of local model or via api
✨ in the sandbox added location selection (upper left corner)
✨ updated failed Ava images
✨ redesign of selection buttons
✨ reworked path to one of the sexual scenes with Dina in the plot
✨ now if koboldcpp is selected and koboldcpp-remote tab kobold in settings is open by default
🛠 minimum screen size in windowed mode increased from 640x360 to 900x500
🛠 improved bots determining location changes and arrival of second character. fixed work on local models via koboldcpp
🛠 maximum temperature value lowered to 1.4, recommended to 0.72
🛠 holiday theme on the main screen extended until january 14

💘 download game :

multiic-win-0377 1.1gb
multiic-win-local-0377 6.4gb
multiic-win-lite-0377 0.6gb
multiic-apk-0377 0.6gb
multiic-linux-0377 1.3gb

*now for windows there will be three options: standard (with koboldcpp), -local (with local model) and -lite (without koboldcpp). for linux u will need to download the model separately and select it in settings (later I will figure out the configuration and make it the same as on windows with the folder resources/koboldcpp). for now it's like this, but I might come to u later for advice :)

windows: koboldcpp with models is located in the folder resources/koboldcpp, all gguf models from this folder the game will load on the start screen and tab in settings

windows/linux: a model from any folder can be loaded from the settings tab by clicking on "select model"

the local model where I stopped - Gemma-2-Ataraxy-v4d-9B.i1-Q4_K_M - by feeling ~ level of chatgpt-3.5, a bit weak, but much better than cosmosrp handles triggers-emojis, I think it should work fine for most users. on my laptop's geforce gtx 1050 ti it gives an average speed, on the edge of uncomfortable

of the models that I tested and that may be more suitable for the game - ChatWaifu_v1.4-Q4_K_M-GGUF - I did not add because it works very slowly on my laptop and I haven't really played with it

0.3.77: local model

Comments

y, I am working on fixing critical bugs; a hotfix will be released tomorrow

Stvoler

I have a few problems. Is there a way to extend the content size of 4096 in the integrated Kobold installation? I get this error all the time: Error generating suggestions -> Warning! Request max_context_length=24000 exceeds allocated context size of 4096. It will be reduced to fit. Consider launching with increased --contextsize to avoid errors. I reduced the max length, but the error still appears. Also, the kobold process will not terminate after Multiic is closed. If I start Multiic again, the koboldccp is available twice and so on.

Touching Evil

damn, is everything okay now?

Stvoler

Sadly it looks as though the google drive already hit the download limit

Rascal


More Creators