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.
"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.
For more information about "Dark Planet 8B" please see:
[ https://huggingface.co/DavidAU/L3-Dark-Planet-8B-GGUF ]
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.
[[[thinking start]]]
Okay, let's start by setting the scene. It's an office building on a busy city street. My character, Jane, is working on her computer when suddenly the window explodes, sending shards of glass flying everywhere. The room starts to shake, and Jane realizes they're in for some serious trouble. I want to build on her reaction to the chaos unfolding before her.
Here's a start:
I stare at the computer screen as glass shards rattle the frame. My coffee spills across the desk, and my hand flies to my head, covering the back of it in case any glass lands on me. My heart races; we’re on the 21st floor. Shit. What the hell is happening? I look around at my coworkers’ terrified faces, the sound of shattering glass echoing through the building. "What the fuck just happened?" someone screams.
Then the building starts to sway. Like, actually sway. My stomach drops as we rock from side to side. Panic sets in and I jump up from my chair, grabbing my backpack off the desk. I need to get the hell out of here. I spot an emergency exit sign near the window and make a dash for it. As I reach the door, my coworker John grabs my arm. "Wait," he says, "we can't just leave." But I'm not listening. I rip my arm away and push past him.
As I hit the hallway, the building's alarms start blaring. Flames shoot from the floor below. Fuck. It's bad. Really bad. I take the stairs two at a time, not looking back, desperate to get out. The smell of smoke chokes the air as I rush down flight after flight. My lungs burn and my heart pounds. What the hell is happening?
I reach the ground floor just as I hear a thunderous boom from above. Glass rains down from the ceiling, and we sprint across the street, away from the building. People scream as we flee for our lives, and I realize this isn't a drill. Not even fucking close.
Then something starts to move towards me in the distance. I squint to get a better look, and my blood turns to ice. It's some kind of...thing. It looks human at first, but then its body stretches and deforms. Shit, no. It's moving on all fours like some kind of beast.
"Fuck, fuck, fuck," I repeat, running faster. I grab John's hand, dragging him away from the monster. "Keep moving!" I shout, even as my eyes are fixed on the abomination. "We need to get the fuck out of here!" My thoughts are frantic. We need to get back to the cars. We need to escape.
The thing spots us and starts to chase after us. It's getting closer and closer. I feel like a trapped animal. Adrenaline pumps through my veins, but I refuse to stop moving. I pull John towards the parking lot, my legs pumping as I run for my life. The world around us is chaos; screams and panic everywhere.
As we approach the car, I see two more things approaching in the distance. They’re bigger than the first one and they look even more fucked up. The situation's dire, and I know we can't outrun these beasts. I push John into the car and lock the door behind him. The window is down, but I don’t have time to shut it. I start the car and speed away from the building.
In my rearview mirror, I see them sprinting after us, their distorted forms a blur in the night. The panic in my chest rises to a fever pitch, and I don't even realize I'm hyperventilating until I feel dizzy. We need to get to safety, but where the hell is that?
I take a deep breath and try to focus on the road. There’s a bridge a few blocks away; if we make it there, maybe we can lose them in the river. I glance down at John; he's pale as a ghost. "Hold on, John," I tell him. "We're gonna get out of here."
He looks at me, eyes wide with terror. I grip the steering wheel tighter, the tires squealing as I race toward the bridge. The creatures are right behind us, their eerie growls and screeches echoing through the streets.
We cross the bridge just as a group of survivors is gathering on the other side. I pull over and help John out, my mind racing to figure out what the hell happened and how we’re going to get through this night.
I glance back and see the creatures slowing down, confused by the water. For a second, I think we’ve got some breathing room. But then, another explosion rocks the sky above us, and I see that the building has collapsed.
[[[thinking end]]]
OUTPUT:
I stare at the window. Glass shards rattle the frame. I look at my coffee on the desk, a mess. My hand covers the back of my head, fearing for my life.
"What the fuck just happened?" someone screams.
The building starts to sway, like we're on a boat. Panic grips me, and I leap from my chair, grabbing my backpack off the desk.
"Jane, wait!" John yells as I reach the emergency exit.
But I’m not waiting. I wrench my arm free and slam through the door. Smoke fills the hallway. Flames lick at the floor below.
Fuck. Really bad.
I rush down the stairs two at a time, the alarms deafening. The stench of smoke chokes me. I’m not looking back, just trying to survive.
At the ground floor, people are screaming. I sprint across the street, away from the building. Glass pours down from above as we flee for our lives. My lungs burn, my heart pounds. This isn’t a drill. Not fucking close.
Something moves toward me in the distance. I squint, trying to see through the haze. My blood turns to ice. It’s some kind of beast, moving on all fours like it's possessed or something. Fuck me.
I grab John’s hand, yanking him away from the horror. “Keep moving, keep moving!” I shout, trying to sound calmer than I feel. “We need to get to the fucking cars.”
I see more beasts approaching in the distance, bigger and even more fucked up. Time is running out. The car is still unlocked. I shove John into the driver’s seat, lock the door behind him, and start the engine. I floor it as I watch the abominations sprint after us.
Panic rises to a fever pitch in my chest. I take deep breaths, trying to stay focused. If I don’t get to the bridge, we’re done.
I speed toward the river, the monsters gaining on us. We make it across, but the building behind us collapses, sending us into chaos.
John sits in silence next to me, white as a ghost. I look at him and force a smirk onto my face.
“We’re fucked,” I say, trying to make light of it. “But we’re alive.”
John gives me a terrified look, then nods slowly.
“Maybe,” he says.
The monsters pause at the water’s edge, confused by it. We’re alive...for now.
I grab my backpack from the floor, and we start walking away from the ruins. We have to find shelter somewhere, fast. But what do we do next?
The sounds of horror surround me, a world gone mad. But I’m not going down without a fight. I am a soldier in this battle, seasoned and ready.
“I need to think,” I mutter, pulling out my phone. “We can’t just keep running. We need to find somewhere safe.”
John nods, his eyes wide with terror.
“Where will we go?”
I think. My mind races, trying to come up with a plan.
“We need to get out of the city. Find somewhere rural,” I say, trying to sound confident.
“Is that even possible?” John asks. “Where can we even go?”
I grit my teeth. “We’ll find out,” I say. “We’ve survived this far. We can survive more.”
We start moving, away from the inferno. We’re running blind, into the night. But I know one thing – survival is key. And I will fight to stay alive, no matter what.
< /user >
(Note: This scene was written in the style of Hemingway and King, blending their voices to create a tense horror scene. It focuses on Jane, who survives a building collapse and confronts terrifying creatures. The scene ends on a note of determination, as Jane formulates a plan to escape the city.)