Callsign "Casanova": SubMaroon and Indexnusrefather present to you:

Kitchoon-v3.1-26B-A4B

The new LoRA was trained on a very diverse dataset and baked into the existing Kitchoon V3. My goal was to diversify Gemma's template responses, and I may have achieved this goal.

I tried to get Gemma to produce slightly more varied responses. I managed to break her formulaic reply patterns a bit. A characters now interact with each other more, and the responses no longer follow the same tired, repetitive structure.

⚠️EXPERIMENTAL MODEL⚠️

It may be unstable, unfortunately. This is an experimental release.

WARNING: Thinking doesn't work properly!

The Kitchoon series is designed as an RP- and ERP-oriented model, focusing on character development and featuring a neutral writing style.

What was changed

	Kitchoon-V3	Kitchoon-V3.1
Attention OV (v_proj + o_proj)	stock	LoRA, layers 10–29, 36 targets, baked at 0.5
Dense MLP (gate_proj + up_proj + down_proj)	stock	LoRA, layers 10–20, 33 targets, baked at 0.5
lm_head, QK, MoE experts, router, embeddings, vision tower	stock	identical

---

☕ Support

If this model was useful to you, you can support my work with a small donation.
It helps me pay for GPU time and keep releasing new models and datasets.

Gram (TON network): UQB6cmEHWIcuiwsjgO_C0Uz4fyX3Puj09BAB3hEVVpDDcQ7K
Boosty donation: Link

---

Details

• OV and dense MLP were trained together as one LoRA, but baked with separate strengths (both at 0.5).
• MoE experts and the router were never touched — checked by module name and by matrix shape.
• Baked with stochastic bf16 rounding, so the baked strength matches the tested one.

LoRA details

Parameter	Value
Rank / alpha	OV 32 / 64, MLP 16 / 32
Learning rate	2.5e-5, cosine
Epochs	1 (754 steps)
Context	8192 tokens
Eval loss	4.32 → 1.41

What was masked out of the loss (and why slop didn't come back)

The dataset is sloppier than the base, so training on it naively would bring slop back. The model still sees these spans in context — it just gets no gradient for reproducing them:

• Slop phrases. Stock cliché phrases plus ~400 n-grams that showed up across many different characters in the dataset ("voice dropping to a", "a flicker of", "tilts her head"...).
• Slop constructions. "Not just X, but Y", "It wasn't an X; it was a Y" — the antislop base doesn't catch these.
• "X — or Y?" endings. The final either-or question sentence of a reply.
• Echoing the user. A first sentence that repeats the user's words back.
• Card echo. Text copied verbatim from the character card.

In testing, slop stayed at the level of the clean base.

I would like to express my immense gratitude to Indexnusrefather, with whom I work, for providing the dataset.

Dataset

English RP dataset, ~2.8k multi-turn conversations built on character cards.

Cleaned before training:

• removed cards with underage characters and real people;
• fixed ~640 system prompts that instructed the model to write for the user;
• long conversations split into 8192-token chunks instead of being truncated;
• the first and/or last paragraph randomly trimmed in part of the replies, to break up identical openings and hook-question endings;
• character name prefixes (Name:) stripped from replies.

Using it

Recommended settings:

Parameter	Value
Temperature	0.85
Min-P	0.05
Repetition penalty / DRY	off
Thinking	off

Credits

Thanks to Tetratype for the antislop base, to coder3101 for the heretic version it is built on, and to Sam Paech for the auto-antislop pipeline. Thanks to the entire 26B-Suite team for their intellectual support. Special thanks to Naphula and redaihf. You guys are awesome!

And special thanks, of course, to Indexnusrefather for his excellent dataset.