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:
- Morrowind - Hilde the Nordish Gladiator (fighting in the Arena in Vivec's city of Morrowind for blood and honor.)
- Morrowind - Male Orc (An Orc that wants to get to Balmora from Seyda Neen.)
- Morrowind - Female Breton (A female Breton with an impressive... heart, wants to join the Mages Guild in Balmora.)
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:
- Original: FP16
- GGUF: Static Quants | iMatrix | High-Attention | iMatrix-High-Attention
- GPTQ: 4-Bit-32
- EXL3: 4.0 bpw | 5.0 bpw | 6.0 bpw | 7.0 bpw | 8.0 bpw
- Specialized: FP8
- Mobile (ARM): Q4_0 | Q4_0_High-Attention
Recommended settings for assistant mode
Full generation settings: Debug Deterministic.
Full generation settings: min_p.
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_Magic — Wild, yet very coherent!
Fiendish — More wild, but still very coherent!
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
- Impish_LLAMA_4B the “Impish experience”, now runnable on spinning rust & toasters.
- SLOP_Detector Nuke GPTisms, with SLOP detector.
- LLAMA-3_8B_Unaligned The grand project that started it all.
- Blog and updates (Archived) Some updates, some rambles, sort of a mix between a diary and a blog.
- Downloads last month
- 48
Model tree for Sicarius-Prototyping/Impish_Longtail_12B
Base model
mistralai/Mistral-Nemo-Base-2407