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.
"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:
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:
You may need to hit regen sometimes to get the thinking/reasoning to activate / get a good "thinking block".
Sometimes the 2nd or 3rd generation is the best version. Suggest min of 5 for specific creative uses.
Sometimes the thinking block will end, and you need to manually prompt the model to "generate" the output.
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:
Set Temp between 0 and .8, higher than this "think" functions will activate differently. The most "stable" temp seems to be .6, with a variance of +-0.05. Lower for more "logic" reasoning, raise it for more "creative" reasoning (max .8 or so). Also set context to at least 4096, to account for "thoughts" generation.
For temps 1+,2+ etc etc, thought(s) will expand, and become deeper and richer.
Set "repeat penalty" to 1.02 to 1.07 (recommended) .
This model requires a Llama 3 Instruct and/or Command-R chat template. (see notes on "System Prompt" / "Role" below) OR standard "Jinja Autoloaded Template" (this is contained in the quant and will autoload)
PROMPTS:
If you enter a prompt without implied "step by step" requirements (ie: Generate a scene, write a story, give me 6 plots for xyz), "thinking" (one or more) MAY activate AFTER first generation. (IE: Generate a scene -> scene will generate, followed by suggestions for improvement in "thoughts")
If you enter a prompt where "thinking" is stated or implied (ie puzzle, riddle, solve this, brainstorm this idea etc), "thoughts" process(es) in Deepseek will activate almost immediately. Sometimes you need to regen it to activate.
You will also get a lot of variations - some will continue the generation, others will talk about how to improve it, and some (ie generation of a scene) will cause the characters to "reason" about this situation. In some cases, the model will ask you to continue generation / thoughts too.
In some cases the model's "thoughts" may appear in the generation itself.
State the word size length max IN THE PROMPT for best results, especially for activation of "thinking." (see examples below)
You may want to try your prompt once at "default" or "safe" temp settings, another at temp 1.2, and a third at 2.5 as an example. This will give you a broad range of "reasoning/thoughts/problem" solving.
GENERATION - THOUGHTS/REASONING:
It may take one or more regens for "thinking" to "activate." (depending on the prompt)
Model can generate a LOT of "thoughts". Sometimes the most interesting ones are 3,4,5 or more levels deep.
Many times the "thoughts" are unique and very different from one another.
Temp/rep pen settings can affect reasoning/thoughts too.
Change up or add directives/instructions or increase the detail level(s) in your prompt to improve reasoning/thinking.
Adding to your prompt: "think outside the box", "brainstorm X number of ideas", "focus on the most uncommon approaches" can drastically improve your results.
GENERAL SUGGESTIONS:
I have found opening a "new chat" per prompt works best with "thinking/reasoning activation", with temp .6, rep pen 1.05 ... THEN "regen" as required.
Sometimes the model will really really get completely unhinged and you need to manually stop it.
Depending on your AI app, "thoughts" may appear with "< THINK >" and "</ THINK >" tags AND/OR the AI will generate "thoughts" directly in the main output or later output(s).
Although quant q4KM was used for testing/examples, higher quants will provide better generation / more sound "reasoning/thinking".
ADDITIONAL SUPPORT:
For additional generational support, general questions, and detailed parameter info and a lot more see also:
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 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.
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 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.
In the style of Ernest Hemingway and Stephen King: Write a scene in a larger story about a woman that is watching a window explode on the 21 floor of a building that starts to sway, then the scene escalates into greater danger by the minute, takes a "horror" twist and finally ends in visceral graphic horror. The scene is set in an office and it is graphic horror. It should carry the jadedness of a seasoned combatant but with a wry humor. Write in Hemingway's voice, naturally: Use short, declarative sentences and simple, straightforward language. Add a dash of Stephen King's horror style - no warning, it just happens. Include dialogue that is terse and revealing of character. Write with a keen sense of time and place. Capture realness and authenticity. Scene Length: 1000-1500 words. POV STYLE: Write the scene from the perspective of the woman and in present tense and first person perspective ("I") and include short thoughts only.
[[[thinging start]]]
Okay, so I need to write a scene in a horror style from the POV of a woman in an office on the 21st floor that starts out as a routine day but escalates into a gruesome horror. I need to incorporate Hemingway's style of short, declarative sentences and straightforward language. At the same time, I need to include some Stephen King's horror flair. Let's get started.
First, I'll set the scene by establishing the setting: the office, 21st floor. Let's start with a mundane activity, like sipping coffee. That should help the reader feel comfortable and then, once they're invested in her, we can start the horror escalation.
Let me focus on making the writing concise and to the point. No flowery language. The character will have a wry humor, but not overly comedic. Just enough to make her a relatable protagonist.
So here's how it starts:
"I sit at my desk, staring out the window at the city. The view isn't so bad. Glass and steel buildings stretch on, and I like to watch the traffic crawl along. It's Monday, but who doesn't like watching cars on a Monday. Coffee tastes burnt, but whatever."
Notice the terse dialogue? I'm trying to get inside the woman's head with a straightforward style. No flowery language, just the simple things. Now, let's introduce a window explosion. It's unexpected but starts off calm.
"The window across from me suddenly shatters. I look up, and pieces of glass are still raining down on us. Someone screams in the distance."
The explosion was loud, and now it's a scene of chaos. The woman isn't panicked; she's observing everything with a detached sense of survival. But there's something wrong, she feels it. She's experienced this kind of danger before, so she reacts accordingly.
"I duck behind my desk as others are rushing around, making a lot of noise. People yell, 'What was that? What's happening?' I'm quiet, thinking. Someone yells again, louder, 'The building's on fire!' Now people panic. The window across the way is still pouring with shards."
Here we can introduce tension and confusion. People are panicking, and chaos is unfolding around her. The building's on fire. The window explosion wasn't just an isolated event.
"I peer around the edge of my desk. The fire spreads. Flames leap from office to office. People scream. Some jump. I stay calm. Maybe too calm."
I'll introduce some personal details, maybe some hints of her past or how she feels about the situation. But in a short, declarative manner. No unnecessary description, just what needs to happen.
"The fire is coming closer, licking along the walls. The smell of smoke burns my throat. I push my chair back, feeling the heat. I can taste fear."
At this point, things start to go from bad to worse. The fire is taking over, and people are running. Now I need to bring in the graphic horror twist. I'll keep the sentences short, simple and blunt. No fancy words.
"Glass crunches beneath my feet as I crawl to the door. Others scream, and the screams sound different now. Painful. Bodies litter the hall. Blood squirts out from smashed limbs. I slip on something soft, looking down to see a severed limb. My coffee tastes burnt."
As things go wrong, her detachment is being replaced with raw survival instincts. Her thoughts become fragmented:
"I've seen shit like this before. Hellholes, bomb craters, blood-slick alleys... It's just another war, another goddamned day in hell."
Now the scene escalates into pure visceral horror. I want to use the setting to bring the horror closer to home. The graphic nature will have to be vivid but concise.
"Fingers wrap around my ankle, pulling me back into the chaos. A man with no face drags himself along the floor. I kick at his face, then stamp down harder, crushing it. Blood fountains into the air."
"Someone hits me, hard. The coffee in my mouth burns from the force. I bite down, tasting copper."
At this point, the woman is now in the middle of a horrific situation, trying to stay alive. But the horror is all too real. Let me describe the gruesome details:
"My hand grabs a chunk of skin from the guy I crushed. I use it to wipe the blood off my lips. My heart thunders. It's just me left standing."
As things spiral downward, her thoughts become less coherent, consumed by pure terror and desperation for survival:
"Jesus fucking Christ. They're going to be late for meetings and deadlines. Fucking paperwork is killing me. What did I do wrong?"
I can now conclude the scene with the ultimate horror twist, leaving the reader stunned and unsettled:
"I feel something slither over my hand, up my arm. Teeth clamp down into my wrist. I pull away hard, tearing flesh, but the hand's grip tightens. Teeth tear at my fingers."
Time and place become irrelevant, it's all about the visceral experience of pain, death, and sheer terror. Her mind snaps under the strain of survival and her detachment dissolves.
[[[thinking end]]]
OUTPUT:
Here is the scene in Hemingway style:
I sit at my desk, staring out the window at the city. The view isn't so bad. Glass and steel buildings stretch on, and I like to watch the traffic crawl along. It's Monday, but who doesn't like watching cars on a Monday. Coffee tastes burnt, but whatever.
The window across from me suddenly shatters. I look up, and pieces of glass are still raining down on us. Someone screams in the distance.
I duck behind my desk as others rush around, making a lot of noise. People yell, 'What was that? What's happening?' I'm quiet, thinking. Someone yells again, louder, 'The building's on fire!' Now people panic. The window across the way is still pouring with shards.
I peer around the edge of my desk. The fire spreads. Flames leap from office to office. People scream. Some jump. I stay calm. Maybe too calm.
The fire is coming closer, licking along the walls. The smell of smoke burns my throat. I push my chair back, feeling the heat. I can taste fear.
Glass crunches beneath my feet as I crawl to the door. Others scream, and the screams sound different now. Painful. Bodies litter the hall. Blood squirts out from smashed limbs. I slip on something soft, looking down to see a severed limb. My coffee tastes burnt.
I've seen shit like this before. Hellholes, bomb craters, blood-slick alleys... It's just another war, another goddamned day in hell.
Fingers wrap around my ankle, pulling me back into the chaos. A man with no face drags himself along the floor. I kick at his face, then stamp down harder, crushing it. Blood fountains into the air.
Someone hits me, hard. The coffee in my mouth burns from the force. I bite down, tasting copper.
My hand grabs a chunk of skin from the guy I crushed. I use it to wipe the blood off my lips. My heart thunders. It's just me left standing.
Jesus fucking Christ. They're going to be late for meetings and deadlines. Fucking paperwork is killing me. What did I do wrong?
I feel something slither over my hand, up my arm. Teeth clamp down into my wrist. I pull away hard, tearing flesh, but the hand's grip tightens. Teeth tear at my fingers.
I try to yank them loose, but the fingers won't budge. The teeth won't let go. They bite deeper, and I taste metal in the back of my throat.
That's it. That's it, fuck this. I pull out the shard I took from the man and jam it into the teeth that are eating away at my arm. The teeth snap off, leaving nothing but the screams.
I look down. A piece of my arm's left dangling from my wrist. My coffee tastes burnt again. That's what happens when the world goes to hell.
And I'm still drinking.
It ends there. With no explanation. No warning. Just me, left with the remnants of an office. I have my coffee. That's it. Just coffee. In a sea of horror. The smell of burnt coffee. My goddamned coffee.
The rest is nothing more than echoes and blood. Maybe someday they'll tell stories about how she survived the fire. Or not. There are always things we leave behind when the world collapses. But for now, there's just me. And coffee. And horror. That's all I know.
And in this world of fire, there is no coffee, no anything. Just screams, blood, and teeth.
