VOOZH about

URL: https://huggingface.co/TheDrummer/Magidonia-24B-v4.3

⇱ TheDrummer/Magidonia-24B-v4.3 · Hugging Face


Join our Discord! https://discord.gg/BeaverAI

More than 9000 members strong 💪 A hub for users and makers alike!


Drummer is open for new opportunities (I'm a Software Engineer). Contact me through any of these channels: https://linktr.ee/thelocaldrummer

Thank you to everyone who subscribed through Patreon. Your support helps me chug along in this brave new world.

FAQ for those out-of-the-loop


Drummer proudly presents...

Magidonia 24B v4.3 💿

👁 image

What's New?

  • Much better roleplay
  • Might refuse/be more positive
  • But much better roleplay

Usage

  • Mistral v7 Tekken
  • [THINK] [/THINK] might work
  • <thinking> </thinking> works
  • No thinking also works

Description

The model often surprises me with how good some of the generated answers are. The overall level is also good.

i'm lurking here for weeks, testing out the builds in RP, this is by far the best one. It is pretty smart and aware of it's surroundings and holds the character card really well.

i tried many of your magistral finetunes and for sure this feels the best so nice job^^

I've completed the analysis of v4zk's response, and it's excellent, with virtually no physics errors or contradictory intentions. This is significantly better than previous versions of Cydonia, which always had obvious trade-offs: either too erotic and lacking in physics, or a balance between physics and eroticism at the expense of character development, or simply inconsistency, performing terribly in certain test cases. v4zk's response is virtually error-free and novel, maintaining broad stability while allowing characters to express distinct inner intentions. I believe this is the best version of Cydonia to date. Simply put, it's good enough to approach the level of Skyfall—making up for most of the gains from parameter scaling.

It's a versatile tune, really adheres to system prompts and thinking prefill. OOC, Author's note and all that work flawlessly. Love the thinking on this one! It's good at reading between the lines when given good prompting. It will consider details from the cards in unique ways. Accepts a wide range of sampling parameters and is still stable (comparatively, it may be too creative at high temperatures). Swipes are minimal compared to other similarly-sized thinking models. Good for RP/CYOA/Dungeon/Chat/Companion/Author!

You can also try its Mistral Small 3.2 counterpart: Cydonia 24B v4.3 (The difference is mostly writing style, and most prefer the Magistral tune.)

Links


👁 image
Thank you to OpenRouter (and esp. @louisgv) for sponsoring my tune and providing me my first ever 'brandkit'!

config-v4zk

Downloads last month
1,573
Safetensors
Model size
415k params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for TheDrummer/Magidonia-24B-v4.3

Collection including TheDrummer/Magidonia-24B-v4.3