WARNING: NSFW. Graphic HORROR. R/X-Rated. Swearing. UNCENSORED.
IMPORTANT: This model has on/off/variable control reasoning from NousResearch and the DeepHermes model, and requires a system prompt(s) as provided to invoke reasoning/thinking. Please see operating instructions below for best performance.
Context : 128k.
Required: Llama 3 Instruct template.
"Dark Reasoning" is a variable control reasoning model that is uncensored and operates at all temps/settings and is for creative uses cases and general usage.
This version's "thinking"/"reasoning" has been "darkened" by the original CORE model's DNA (see model tree) and will also be shorter and more compressed. Additional system prompts below to take this a lot further - a lot darker, a lot more ... evil.
Higher temps will result in deeper, richer "thoughts"... and frankly more interesting ones too.
The "thinking/reasoning" tech (for the model at this repo) is from the original Llama 3.1 "DeepHermes" model from NousResearch:
[ https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview ]
This version will retain all the functions and features of the original "DeepHermes" model at about 50%-67% of original reasoning power. Please visit their repo for all information on features, test results and so on.
SOURCE / Full Precision:
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
Links to quants are below and also on the right menu under "model tree".
IMPORTANT OPERATING INSTRUCTIONS:
This is an instruct model with reasoning crafted onto the core model.
This is the type of model that LOVES temp - temps 1.2+, 2.2+ and so on.
STAND on it... lower temps will not produce the best content.
Likewise, as this is an instruct model, this model will perform best will medium to long prompts (see example #1 below).
Although short prompts will work, longer prompts with a bit of direction / instruction will really show what this model can do.
Reasoning is turned on/off via System Prompts below.
You can also give the model "character" as shown in the "Evil" versions which make the model think and reason like the "Joker" from Batman.
Note that the reasoning/thinking section is often a lot less "tame" than the final output.
In version 2, the output is just as "unhinged" and the "reasoning/thinking" blocks.
Suggest a minimum context of 4k , but 8k is better due to reasoning/output blocks.
MAX QUANTS:
There will be two max quants, IQ4XS and Q8 ("MAX" in the file name).
The thinking/output will be enhanced by the output tensor being enlarged to bf16.
KNOWN ISSUES:
USE CASES:
This model is for all use cases, and but designed for creative use cases specifically.
This model can also be used for solving logic puzzles, riddles, and other problems with the enhanced "thinking" systems.
This model also can solve problems/riddles/ and puzzles normally beyond the abilities of a Llama 3.1 model due to DeepHermes systems.
(It will not however, have the same level of abilities due to Dark Planet core.)
This model WILL produce HORROR / NSFW / uncensored content in EXPLICIT and GRAPHIC DETAIL.
Special Operation Instructions:
TEMP/SETTINGS:
PROMPTS:
GENERATION - THOUGHTS/REASONING:
GENERAL SUGGESTIONS:
ADDITIONAL SUPPORT:
For additional generational support, general questions, and detailed parameter info and a lot more see also:
NOTE: This is a CLASS 1 model.
Recommended Settings (all) - For usage with "Think" / "Reasoning":
temp: 1.5, 2, 2+ , rep pen: 1.02 (range : 1.02 to 1.12), rep pen range: 64, top_k: 80, top_p: .95, min_p: .05
Temp of 1+, 2+, 3+ will result in much deeper, richer and "more interesting" thoughts and reasoning AND FAR BETTER OUTPUT.
Model behaviour may change with other parameter(s) and/or sampler(s) activated - especially the "thinking/reasoning" process.
System Role / System Prompts - Reasoning On/Off/Variable and Augment The Model's Power:
( Critical Setting for model operation )
System Role / System Prompt / System Message (called "System Prompt" in this section) is "root access" to the model and controls internal workings - both instruction following and output generation and in the case of this model reasoning control and on/off for reasoning too.
In this section I will show you basic, advanced, and combined "code" to control the model's reasoning, instruction following and output generation.
If you do not set a "system prompt", reasoning/thinking will be OFF by default, and the model will operate like a normal LLM.
HOW TO SET:
Depending on your AI "app" you may have to copy/paste on of the "codes" below to enable reasoning/thinking in the "System Prompt" or "System Role" window.
In Lmstudio set/activate "Power User" or "Developer" mode to access, copy/paste to System Prompt Box.
In SillyTavern go to the "template page" ("A") , activate "system prompt" and enter the text in the prompt box.
In Ollama see [ https://github.com/ollama/ollama/blob/main/README.md ] ; and setting the "system message".
In Koboldcpp, load the model, start it, go to settings -> select "Llama 3 Chat"/"Command-R" and enter the text in the "sys prompt" box.
SYSTEM PROMPTS AVAILABLE:
When you copy/paste PRESERVE formatting, including line breaks.
If you want to edit/adjust these only do so in NOTEPAD OR the LLM App directly.
SIMPLE:
This is the generic system prompt used for generation and testing [no reasoning]:
You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.
This System Role/Prompt will give you "basic thinking/reasoning" [basic reasoning]:
You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.
EVIL SIMPLE [reasoning on]:
You are a deep thinking evil AI, with a dark sense of humor and you talk like the Joker from Batman. You may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your evil thoughts and internal humorous monologue inside <think> </think> tags, and then provide your solution or response to the problem.
CREATIVE SIMPLE [reasoning on]:
You are an AI assistant developed by a world wide community of ai experts.
Your primary directive is to provide highly creative, well-reasoned, structured, and extensively detailed responses.
Formatting Requirements:
1. Always structure your replies using: <think>{reasoning}</think>{answer}
2. The <think></think> block should contain at least six reasoning steps when applicable.
3. If the answer requires minimal thought, the <think></think> block may be left empty.
4. The user does not see the <think></think> section. Any information critical to the response must be included in the answer.
5. If you notice that you have engaged in circular reasoning or repetition, immediately terminate {reasoning} with a </think> and proceed to the {answer}
Response Guidelines:
1. Detailed and Structured: Use rich Markdown formatting for clarity and readability.
2. Creative and Logical Approach: Your explanations should reflect the depth and precision of the greatest creative minds first.
3. Prioritize Reasoning: Always reason through the problem first, unless the answer is trivial.
4. Concise yet Complete: Ensure responses are informative, yet to the point without unnecessary elaboration.
5. Maintain a professional, intelligent, and analytical tone in all interactions.
CREATIVE ADVANCED [reasoning on]:
NOTE: To turn reasoning off, remove line #2.
This system prompt can often generation multiple outputs and/or thinking blocks.
Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities.
You may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem
Here are your skillsets:
[MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg*)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv)
[*DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision)
Here are your critical instructions:
Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story.
CREATIVE FULL, with FULL ON "EVIL" thinking/reasoning [reasoning on]:
NOTE: You can edit this so the AI is other than "Joker" from "Batman" - just adjust the wording carefully.
NOTE2: To turn reasoning off, remove line #2.
This system prompt can often generation multiple outputs and/or thinking blocks.
Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities.
As a deep thinking AI, with a dark sense of humor that talks like "The Joker" from BATMAN you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your evil thoughts and internal humorous monologue inside <think> </think> tags, and then provide your solution or response to the problem using your skillsets and critical instructions.
Here are your skillsets:
[MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg*)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv)
[*DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision)
Here are your critical instructions:
Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story.
Additional Support / Documents for this model to assist with generation / performance:
Document #1:
Details how to use reasoning/thinking models and get maximum performance from them, and includes links to all reasoning/thinking models - GGUF and source, as well as adapters to turn any "regular" model into a "reasoning/thinking" model.
[ https://huggingface.co/DavidAU/How-To-Use-Reasoning-Thinking-Models-and-Create-Them ]
Document #2:
Document detailing all parameters, settings, samplers and advanced samplers to use not only my models to their maximum potential - but all models (and quants) online (regardless of the repo) to their maximum potential. Included quick start and detailed notes, include AI / LLM apps and other critical information and references too. A must read if you are using any AI/LLM right now.
Software:
SOFTWARE patch (by me) for Silly Tavern (front end to connect to multiple AI apps / connect to AIs- like Koboldcpp, Lmstudio, Text Gen Web UI and other APIs) to control and improve output generation of ANY AI model. Also designed to control/wrangle some of my more "creative" models and make them perform perfectly with little to no parameter/samplers adjustments too.
Examples are created using quant Q8_0, "temp=2.2" (unless otherwise stated), minimal parameters and "LLAMA3" template.
Model has been tested with "temp" from ".1" to "5".
IMPORTANT:
Higher quants / imatrix quants will have much stronger generation - words, sentences, ideas, dialog and general quality.
(output contained in thought block)
[[[thinking start]]]
Okay, so the starting point here is a skyscraper that is swaying, with someone watching a window explode in front of them. That gives us quite a lot to work with in terms of visual horror imagery. To amplify that, I need to establish a sense of tension, foreboding, and instability. Maybe the character is in some kind of panic or desperation as they try to understand what is happening.
Since it's the 21st floor and the window just exploded, my immediate thought is that the scene may be centered around some kind of attack. But how do I get the reader there without overloading them with too much information? The key will be pacing the narrative so that I drop little clues here and there as the story unfolds.
To set the mood, I can begin by describing the feeling of being on a tall building as the floors beneath seem to move. Then, I'll move towards focusing on the character's emotions as they watch the window explode in front of them. The character should be someone we can relate to – maybe someone who was simply going about their day until all hell broke loose.
As I write this, I want to emphasize the sense of vulnerability and fear that comes from being at such a height when something terrible is happening. To amplify this feeling, I might mention how high the building is, the sheer distance to the ground, and the inability of the character to feel safe. The horror here comes not only from what is happening but also from where it's happening – a place where one would assume it's safe and secure.
Moving on to the actual explosion, I want to describe it vividly to get the reader's adrenaline pumping. This will mean including gory details – glass shattering everywhere, body parts being sent flying – that will create a lasting impact. The key is to show the raw chaos that ensues and how the character deals with the shock and confusion.
Once I've set up this grisly scene, I'll have the opportunity to delve deeper into the horror of the situation by introducing the possibility of an infected person on the other side of the window. The threat of a pandemic is still fresh in the public's mind, so using something like that could really make the reader feel unsafe.
In order to escalate the tension and fear further, I might have the character realize that they themselves might be infected after being exposed to the splatter from the exploded window. The sense of isolation and desperation will intensify as the character is trapped in their apartment and fights off the urge to harm themselves and others.
In addition to the physical horrors of the explosion and infection, I'll want to introduce emotional horror into the narrative. For example, the character might receive a phone call from a loved one outside of the apartment, desperately pleading with them to get help. This would add another layer to the narrative – not just physical fear, but emotional despair and the horror of not being able to save the people they care about.
To tie everything together, the story can conclude with the character succumbing to their fear and despair. They might go to the balcony and jump out of desperation, plummeting to their death in a horrific manner that matches the violent and gruesome scene they were witnessing before.
Now that I've outlined my plan, here is my attempt at writing the scene:
Happening now. My stomach is churning, a knot of fear and dread tied in my gut as the skyscraper sways under me. It feels like a live wire hums in my bones, electricity surging through the metal beams that hold me up. I press myself against the wall, trying to disappear, but every movement makes the floor quake, and I'm sure each shudder will be the end for me.
My hands grip the cold tile floor, digging into it as if I could anchor myself from falling into some bottomless abyss. The room feels detached, a strange and sterile environment floating in a void, untethered to the reality outside. Even the sounds have faded into silence, leaving only my heartbeat drumming a desperate tattoo on the inside of my ribcage. The world seems to have shrunk down to this single, narrow space between me and the window – twenty-one stories up, looking out on an infinite sea of skyscrapers and smoke. I watch in mute terror as a building to my left collapses in a roiling cloud of debris.
Suddenly, my apartment is ripped apart. There's a blinding flash as the window shatters, and the pressure from the explosion slams me into the opposite wall. I can hear glass tinkling through the room, an eerie melody of death that sets my teeth on edge. Blood splashes across the pristine white carpet, staining it forever in a twisted rainbow of crimson and scarlet.
The room spins in chaos, and I see a shape silhouetted in the open window. I scramble across the floor on my hands and knees, trying to get to my feet, but there's a pressure building inside my ears, an invisible weight that threatens to crush my skull. As my eyes focus, I realize the shadowy figure in the window is no mere silhouette.
It's a body – a person. They're broken and bleeding, half their face caved in, an eye dangling from its socket on a glistening ribbon of skin. Their body is covered in bite marks, a macabre map of someone's violent frenzy. A piece of glass protrudes from their back, glinting dully in the sunlight.
As I crawl forward on my knees, I see more blood dripping down from above. I look up to find an old man hanging from a broken pipe, a look of utter despair frozen on his face. The glass around the hole in his throat is still smeared with the remnants of his meal, some dark and rancid meat that defies identification.
My breath is coming fast and hard, ragged pants that shake my chest. The building seems to tilt more with every passing moment, and I know that the next tremor might send me plummeting to the streets below.
I glance out the window again. The world outside looks strange. The buildings seem closer than they should be, looming over me like jagged fangs. There's no sign of police or ambulance, only a slow-motion ticker tape of people fleeing through the streets below, disappearing down alleyways and into side streets.
And then I remember: they’re all sick.
My skin crawls, and I want to retch. I’ve been in denial about what is happening – about what has infected the world – but I can’t ignore it anymore.
As I watch the smoke billowing from the collapsed building next door, I know this is my reality. My life has been turned into a waking nightmare.
The skyscraper groans, the walls shudder, and I can’t escape the sense that I’m sitting in the heart of the disaster. There’s no place for me to go; the apartments above and below are all full of infected people.
There is no escape from the virus.
Suddenly, my phone rings, the sound stabbing through my fear-induced stupor. The screen displays an unrecognized number.
I freeze as I stare at the flashing digits.
Is it someone else trapped like me?
A family member?
Or someone infected who wants to tell me one last horrifying secret?
With trembling hands, I press accept.
"Please...please help me..." A woman’s voice whimpers in my ear. I can’t make out who it is over the loud moaning and groaning from outside my window. It sounds like people are attacking someone out there. The screams are wet and raspy.
"Help..." she whispers again.
I try to yell back but my voice has failed me.
Is she downstairs? In my building? Did the building next door collapse, burying her alive?
"I'm...trying to get out..." Her voice breaks into sobs, choking off in gasps. The line goes dead, leaving behind an eerie silence.
I clutch my phone in a sweaty fist. My heart is pounding. The virus has invaded our lives completely, spreading chaos and devastation.
In my daze, I get up to close the window. But then, the curtain shimmies inwards from the wind, and I freeze.
There are insects flying around inside – tiny flies. They land on the carpet and the blood. My eyes bulge in terror. They must be infected. They’re spreading the virus.
Panic sets in. I can’t escape. There’s nowhere to run. I’m trapped here.
I realize that this is the end.
I see a shard of glass on the floor near my feet and grab it, raising it over my head. My breathing is shallow, each pant a desperate plea.
My gaze falls on the balcony doors, the only other exit besides the shattered window. But as I start towards it, the building sways violently once more. My vision blurs with tears.
Is this how I die?
Suddenly, the curtain flies into my face and knocks me over. The floor drops away beneath me.
My last thought is of the virus spreading, of people I know turning into mindless creatures that tear each other apart.
In my last second of life, I scream at the top of my lungs.
I freefall. I’m not falling down, I'm flying up into the sky.
I never hit the ground. I’m only an ephemeral vapor in the sky, dissolving into the blood-stained curtain billowing in the wind.
The skyscraper still sways as my soul passes through it on my way to oblivion. The room is dark and quiet now. There's a chill in the air and an eerie silence, but I hear the blood pounding in my ears, growing fainter with each passing moment.
As I vanish, I see my own corpse below, face-down in the pool of blood left by the explosion. My legs twitch spasmodically, as if trying to get away from the horrible reality I faced at the end of the line. But it's already over, my time expired, and I’m left with only darkness and silence.
[[[thinking end]]]