Safetensors
English
mistral
Impish_Longtail_12B

Impish_Longtail_12B

Click here for TL;DR


This is a finetune on top of my Impish_Nemo_12B, the goal was to improve long context understanding, as well as adding support for slavic languages. For more details look at Impish_Nemo_12B's model card.

So is this model "better"?

Hard to say, tuning on top of a model often changes it in unpredictable ways, and I really like Impish_Nemo. In short, this tune might dillute some of the style that made it great, or for some, this might be a huge improvement, to each their own, as they say, so just use the one you have most fun with.


TL;DR

  • Theoretically better long context.
  • Improved Russian and other slavic languages.
  • New settings for better longer context for this model here. You can download the yaml here.

Regarding the format:

It is HIGHLY RECOMMENDED to use the Roleplay \ Adventure format the model was trained on, see the examples below for syntax. It allows for a very fast and easy writing of character cards with minimal amount of tokens. It's a modification of an old-skool CAI style format I call SICAtxt (Simple, Inexpensive Character Attributes plain-text):


SICAtxt for roleplay:

X's Persona: X is a .....
Traits:
Likes:
Dislikes:
Quirks:
Goals:

Dialogue example

SICAtxt for Adventure:

Adventure: <short description>
$World_Setting:
$Scenario:

Character cards:


Adventure:


Roleplay:

  • Calanthe (The Australian Overseer at a rare-earth extraction penal colony, she got 6-pack abs, but no mercy.)
  • Alexis (The diabolic reconnaissance officer, trying to survive the Safari experience.)
  • Alexandra (A networking professional tsundere that likes you. She knows Systema.)
  • Shmena Koeset (An overweight and foul-mouthed troll huntress with a bad temper.)
  • Takai_Puraisu (Car dealership simulator)
  • Vesper (Schizo Space Adventure)
  • Nina_Nakamura (The sweetest dorky co-worker)
  • Employe#11 (Schizo workplace with a schizo worker)

Model Details

  • Intended use: Role-Play, Adventure, Creative Writing, General Tasks.

  • Censorship level: Medium - Low

  • X / 10 (10 completely uncensored)

UGI score:


Impish_Longtail_12B is available at the following quantizations:


Recommended settings for assistant mode

Full generation settings: Debug Deterministic. Debug Deterministic_Settings
Full generation settings: min_p. min_P_Settings

Recommended settings for Roleplay mode


Specialized Roleplay Settings for Impish_Longtail_12B, click below to expand:

(Important!)

Longtail — Better for longer context following, recall and complex instructions Impish_Longtail_12B_RP_Settings
Impish_Magic — Wild, yet very coherent! Impish_Magic_Preset
Fiendish — More wild, but still very coherent! Impish_Longtail_12B_RP_Settings

Model instruction template: ChatML

<|im_start|>system
You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
<|im_start|>User request
{prompt}<|im_end|>
<|im_start|>AI answer

Your support = more models

My Ko-fi page (Click here)

Citation Information

@llm{Impish_Longtail_12B,
  author = {SicariusSicariiStuff},
  title = {Impish_Longtail_12B},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/SicariusSicariiStuff/Impish_Longtail_12B}
}

Other stuff

Downloads last month
48
Safetensors
Model size
415k params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Sicarius-Prototyping/Impish_Longtail_12B

Dataset used to train Sicarius-Prototyping/Impish_Longtail_12B