allura-org/MN-12b-RP-Ink

Nemo 12b RP Ink

A roleplay-focused LoRA finetune of Mistral Nemo Instruct. Methodology and hyperparams inspired by SorcererLM and Slush.
Renamed to Ink to distinguish from [insert every other rp tune ever], but it's the same data as was used in the Teleut RP model.

Testimonials

dude Fizz, Ink is fucking gas

- inflatebot

First impression, I put this higher than Rocinante and Magnum Picaro

- ShotMisser64

Never tried 12B, but this one is GOAT

- Evoc

Dataset

The worst mix of data you've ever seen. Like, seriously, you do not want to see the things that went into this model. It's bad.

"this is like washing down an adderall with a bottle of methylated rotgut" - inflatebot

Quants

• Static GGUFs (thanks auri!)
• Imatrix GGUFs (thanks bart!)

Recommended Settings

Chat template: Mistral v3-Tekken
Recommended samplers (not the be-all-end-all, try some on your own!):

• Temp 1.25 / MinP 0.1
• Temp 1.03 / TopK 200 / MinP 0.05 / TopA 0.2

Hyperparams

General

• Epochs = 2
• LR = 6e-5
• LR Scheduler = Cosine
• Optimizer = Paged AdamW 8bit
• Effective batch size = 12

LoRA

• Rank = 16
• Alpha = 32
• Dropout = 0.25 (Inspiration: Slush)

Credits

Humongous thanks to the people who created the data. I would credit you all, but that would be cheating ;)
Big thanks to all Allura members, especially Toasty, for testing and emotional support ilya /platonic
Also special thanks to Bot for making the model card image here :3