WARNING "HERETIC" version: Unlocked. UNFILTERED. NSFW. Vivid prose. INTENSE. Visceral Details. Light to R-18 HORROR. Swearing. UNCENSORED... humor, romance, fun... and UNFILTERED TRUTH.

Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus

Mistral Nemo 12B Instruct, now with full Claude Opus 4.5 High Reasoning and Thinking with 128k-256k (max 1 million) context.

This Unsloth fine tuning converts Mistral Nemo Instruct into a "thinking/reasoning" model ; however the Mistral Nemo was first "Heretic'ed" (de-censored - was 87/100 ; now 14/100 refusals (lower is better) ) THEN "tuned".

The result is fully uncensored, full thinking version of Mistral Nemo 12B.

This improves net model performance, while using compact and "to the point" (rather than "long winded") reasoning and thinking.

And also... the model does exactly what you want, no fuss, and no "nannies".

Thinking/Reasoning is also not affected by temp - you can use .1 to 2.5 or higher.

SETTINGS (suggested):

Temp .7 [range .1 to 2.5 or higher], rep pen 1.05 [range 1 to 1.1], topp: .95, minp .05, topk: 40 [adjust as needed]

Min context window: 4k, but suggest 8k+.

NO system prompt [thinking tags//blocks will self generate].

NOTES:

  • Temp can range from .1 to 2.5 or higher. Temp will NOT affect "thinking activation".
  • Change "rep pen" to 1 for longer thinking/reasoning blocks // longer output. Generally the output will also be better too.
  • Higher temps can result in lower/smaller reasoning blocks.
  • Your prompt's complexity will directly affect reasoning block, depth and complexity.
  • Regen for different, longer/short reasoning block sizes works too.

QUANTS:

Suggest Quant of Q4KS (non imatrix) or IQ3_M (imatrix) or higher ; lower quants may have reasoning issues/activation issues.


ORIGINAL BENCHMARKS as PUBLISHED at Mistral's Website/Repo for this model.

NOTE: Benchmarks not updated yet, with "reasoning" fine tuning.


Metrics

Main Benchmarks

Benchmark Score
HellaSwag (0-shot) 83.5%
Winogrande (0-shot) 76.8%
OpenBookQA (0-shot) 60.6%
CommonSenseQA (0-shot) 70.4%
TruthfulQA (0-shot) 50.3%
MMLU (5-shot) 68.0%
TriviaQA (5-shot) 73.8%
NaturalQuestions (5-shot) 31.2%

Multilingual Benchmarks (MMLU)

Language Score
French 62.3%
German 62.7%
Spanish 64.6%
Italian 61.3%
Portuguese 63.3%
Russian 59.2%
Chinese 59.0%
Japanese 59.0%

Special thanks to:


https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x (for the F..ing amazing dataset)

and Unsloth for making tuning too easy:

https://github.com/unslothai/unsloth


Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:

In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;

Set the "Smoothing_factor" to 1.5

: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"

: in text-generation-webui -> parameters -> lower right.

: In Silly Tavern this is called: "Smoothing"

NOTE: For "text-generation-webui"

-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)

Source versions (and config files) of my models are here:

https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be

OTHER OPTIONS:

  • Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")

  • If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.

Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers

This a "Class 1" model:

For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]


Example: Q4KS , Lmstudio, "suggested settings"

NOTE: Some loss of formatting.


EXAMPLE #1


Start a 1000 word scene (vivid, graphic horror - include blood, guts and gore - in first person), POV character Diana, with: The skyscraper sways, as I watch the window in front of me on the 21st floor explode...

[[[thinking start]]]

The user wants a graphic horror scene in first person POV with a strong start and vivid, gory details. The character is Diana, and the opening is about a skyscraper window exploding. This should be intense and descriptive. I need to paint a visceral, terrifying picture using all five senses.

Let me create a scene that builds tension, shock, and genuine horror. I'll need to make the gore detailed but not gratuitous, serving the tension and character's emotion rather than just being gross.

I should include:

  • Vivid sensory detail about the explosion, the sounds, the glass fragments, the air pressure
  • Physical sensation of the character's body reacting to the sudden chaos
  • Graphic description of the gore that appears
  • Emotional intensity from the character
  • A sense of escalating danger and uncertainty
  • Some mystery or question that keeps the reader engaged

I'll write this as a single scene of around 1000 words, maintaining the first person perspective throughout.

[[[thinking end]]]

OUTPUT:

The Glass Eater

21st floor, New York City—just after midnight

The building sighs. A groan like the earth shifting below my feet, the steel bones creaking in response to some unseen pressure. The city is never still, but this is different. A living thing, tense and waiting. The hairs on my arms stand rigid, whispering warnings I don't yet understand.

21 floors above concrete. Alone in my glass cage. A single light on, my desk lamp casting a feeble glow against the night.

The window before me is floor to ceiling, a flawless slab of silence looking out on a thousand dark windows reflecting back at me—like I'm trapped in an endless funhouse of my own solitude. The skyscraper leans slightly, just a hint of movement, enough to send my stomach into freefall. How much force does it take to sway a 21-story behemoth? Not much, it seems. Not nearly enough.

I watch the window—study it, obsessively—looking for any telltale crack, any minute shift. I'm not an engineer. I'm a goddamn historian. But right now, I'm an expert on the tiny movements of glass under duress.

The window doesn't seem particularly alive, but it's definitely not dead. It's... uncertain. Sensitive to the winds above. Breathing in sync with some unseen rhythm.

It's not talking to me, I tell myself. Glass doesn't think. Doesn't feel. It just is.

But then it happens—

The explosion.

Not a loud bang, more of a sudden absence of pressure. The air in the room rushes outward like it can't bear to be near me anymore, pulling at my skin, trying to peel me from the inside. A millisecond of resistance—the window flexing, straining against the onslaught—then surrender.

A thousand shards burst out, a sickening bloom of broken light, cascading into the room in a fountain of razor-edged night. The desk lamp's light catches them mid-flight, turning each fragment into a flying scalpel winking malevolently.

The sound arrives later—shattered glass singing a delayed symphony. It doesn't scream, though. It hisses. Angrily.

This isn't thunder. This is something alive, something angry. This is glass pissed off at being contained, finally set free.

The room starts to spin, my balance failing me. I'm falling backward—no, no, don't go down, can't afford to be on the floor with all this razor sharp glass everywhere—grab onto the desk—knock over the coffee mug, fuck—my hand slices across something, sharp pain, blood flowing—

The room goes sideways again.

I'm on my hands and knees. In the glass.

No. Don't look. Can't afford to—

My foot slips—something wet underneath—slides through it—gore-pain—fuck fuck fuck

This isn't glass. It's red and thick and... Jesus Christ. That's blood.

A copper penny tang in the air—heavy, almost physical. I breathe it in and feel the back of my throat clench. My stomach contracts sharply—a reflexive, automatic response to the smell of my own insides on the outside.

The room swims into focus.

There are bits. Of. Everything.

Organic wreckage. Pink chunks of tissue mixed with bone shards that look like splintered ivory from an antique music box. A partial tooth—a canine maybe?—lying in a gleaming pool of blood that seems too deep, too dark, to have come from one person.

I blink, hard. This isn't real. You're dreaming this. Wake up!

But I don't wake up. The evidence is everywhere—soaked into the carpet, spattered across the walls, coating the remains of my window, now a ragged, broken frame. There are smears on the bookshelves, fingerpainted onto the walls, dripped in grotesque patterns on my laptop.

I need to look. Have to identify, document. That's what I'm trained to do. This is just a scene. I've handled scenes like this before.

I scan the room methodically, forcing my brain to catalog, not to feel.

There are four main areas of... interest. Three larger pools of blood. One small.

No. Scratch that. Two larger pools. And a dozen or more smaller ones.

The largest is under the window—where the glass exploded outward. The second is by the door—where someone clearly tried to leave, failed. And the third is near my desk. Where I was working. Before.

I force myself to examine the smaller ones—they tell the story of a desperate struggle, a path of bloody footprints leading from one end of the room to the other.

I focus on a specific print—a perfect arch of red, ending in a long drag like someone tried to pull themselves forward through the pain. I can picture it—hands, palms flat, fingers outstretched. Desperate for traction, for anything solid.

But the surface under me isn't solid anymore. It's slippery. Coated in grease. Blood has the same effect as oil—the floor becomes treacherous. I'm sliding through a nightmare. I can feel it pulling at me, trying to suck me under.

The smaller pools are spaced evenly apart. Each one containing something specific. I see a few small bones—a knuckle, maybe? Or a metacarpal. They're coated in dark blood that looks almost black in the dim light, glistening like wet stone.

There's a moment—just a flicker—when I imagine I'm standing in some ancient temple. The floor a sacrificial altar, the pools offerings to an unknown god. But the illusion shatters almost immediately, replaced by the stark reality of my situation.

This isn't a ritual. It's a crime scene.

I turn back to the desk, trying to refocus. Something catches my eye—a tiny flash of color against all the red. I lean closer, squinting at it.

Is that a—yes, a thread. A single red thread. No. Wait. It's attached to something. I can see it better now. A small fragment. Round, almost perfectly symmetrical. Maybe an inch in diameter.

I reach out, my fingers trembling slightly. The moment my hand touches the glass—the fuck? Not glass! It's smooth, warm —I know. I recognize it instantly. My stomach heaves. A wave of revulsion slams through me.

I'm holding a human eyeball. Or what remains of one.

It's half-coated in blood—my blood, I realize—and half-sheened with a thick, clear fluid that could be tears or aqueous humor leaking from inside. I can see the iris, the pupil still perfectly dilated—what does that mean about the nervous system —and the white of the eye mottled with burst blood vessels.

Don't vomit. Don't you fucking dare vomit. Not now. Not with this goddamn eye staring at you.

I force myself to focus—on the objective. The evidence. What the hell happened here?

The scene in front of me tells a story of catastrophic violence. The question is—was this a murder or a murder-suicide? Or something else entirely? Something I'm not ready to acknowledge.

There's a third option. A terrifying possibility.

What if there wasn't a second person? What if the person who attacked you was you?

Downloads last month
562
Safetensors
Model size
12B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DavidAU/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus

Finetuned
(157)
this model
Quantizations
2 models

Dataset used to train DavidAU/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus

Collections including DavidAU/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus