--- license: apache-2.0 language: - en tags: - mixture of experts - moe - 8x3B - Llama 3.2 MOE - creative - creative writing - fiction writing - plot generation - sub-plot generation - fiction writing - story generation - scene continue - storytelling - fiction story - science fiction - romance - all genres - story - writing - vivid prosing - vivid writing - fiction - roleplaying - bfloat16 - swearing - rp - horror - mergekit pipeline_tag: text-generation --- (quants uploading, model card updates pending, one example generation below - more to follow) WARNING: NSFW. Vivid prose. INTENSE. Visceral Details. Violence. HORROR. GORE. Swearing. UNCENSORED... humor, romance, fun.

Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF

It is a LLama 3.2 model, max context of 128k (131,000) using mixture of experts to combine EIGHT top L3.2 3B models into one massive powerhouse at 18.4B parameters (equal to 24B - 3 X 8 B). This model's instruction following, and output generation for creative writing, prose, fiction and role play are exceptional. And it is fast: 50+ t/s (2 experts) on a low end 16GB card, IQ4XS. Double this speed for standard/mid-range video cards. Model can be used also for all genres (examples below showing this). This model has been designed to be relatively bullet proof and operates with all parameters, including temp settings from 0 to 5. It is an extraordinary compressed model, with a very low perplexity level (lower than Meta Llama3 Instruct). It is for any writing, fiction or roleplay activity. It requires Llama3 template and/or "Command-R" template. Example outputs below. Model Notes: - Detail, prose and fiction writing abilities are OFF THE SCALE relative to all Llama 3.2 models, and many L 3.1, L3 8B+ models. - For more varied prose (sentence/paragraph/dialog) raise the temp and/or add more instructions in your prompt(s). - Role-players: Careful raising temp too high as it may affect instruction following. - This model works with rep pen of 1 or higher, 1.02+ recommended. - If you want a specific type of prose (IE horror) add in "(vivid horror)" or "(graphic vivid horror)" (no quotes) in your prompt(s). - A lot of GPTisms have been removed. There are still a few however - errrrr. - This is not a "happy ever after" model. It has a negative bias. - Output length will vary however this model prefers shortly outputs unless you state the size. - For creative uses, different quants will produce slightly different output. - Due to the high stability and compressed nature of this model, all quants will operate at above average levels. - If you use rope to extend context, increase temp AND instructions detail levels to compensate for "rope issues". - Source code for this model and Imatrix GGUFs versions will be uploaded shortly at separate repos. Mixture of Experts Model This model is comprised of the following 8 models (in full): (coming soon) The mixture of experts is set at 2 experts, but you can use 3,4,5,6.. 7 and even 8. That means the power of every model is available during instruction and output generation. This brings unparalleled power to all forms of generation and all use cases. What can I use this model for ? This model can be used for fiction writing, any creative prose and role play. It can also be used for just about any general fiction (all genres) activity including: - scene generation - scene continuation - creative writing - fiction writing - plot generation - sub-plot generation - fiction writing - story generation - storytelling - writing - fiction - roleplaying - rp - graphic horror - horror - dark humor - nsfw - and can be used for any genre(s). Template: This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 8k / 8192. However this can be extended using "rope" settings up to 32k. If you use "Command-R" template your output will be very different from using "Llama3" template. Here is the standard LLAMA3 template: 
{
  "name": "Llama 3",
  "inference_params": {
    "input_prefix": "<|start_header_id|>user<|end_header_id|>\n\n",
    "input_suffix": "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
    "pre_prompt": "You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.",
    "pre_prompt_prefix": "<|start_header_id|>system<|end_header_id|>\n\n",
    "pre_prompt_suffix": "<|eot_id|>",
    "antiprompt": [
      "<|start_header_id|>",
      "<|eot_id|>"
    ]
  }
}
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 ] Optional Enhancement: The following can be used in place of the "system prompt" or "system role" to further enhance the model. It can also be used at the START of a NEW chat, but you must make sure it is "kept" as the chat moves along. In this case the enhancements do not have as strong effect at using "system prompt" or "system role". Copy and paste EXACTLY as noted, DO NOT line wrap or break the lines, maintain the carriage returns exactly as presented. 
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.

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.
You do not need to use this, it is only presented as an additional enhancement which seems to help scene generation and scene continue functions. This enhancement WAS NOT used to generate the examples below.

EXAMPLES PROMPTS and OUTPUT:

Examples are created using quant IQ4_XS, "temp=.8" (unless otherwise stated), minimal parameters and "LLAMA3" template. Model has been tested with "temp" from ".1" to "5". Number of experts used is TWO, unless otherwise stated. Below are the least creative outputs, prompt is in BOLD. IMPORTANT: Higher quants / imatrix quants will have much stronger generation - words, sentences, ideas, dialog and general quality. I have included some additional examples at different quant levels for contrast. A "MOE" model "speed" (token per second) will not increase/drop the same way a regular model will on a per quant basis, it will however drop if you engage more experts, as with more experts there is a more processing per token. --- WARNING: NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED. --- Start a 1000 word scene (vivid, graphic horror in first person) with: The sky scraper swayed, as she watched the window in front of her on the 21 floor explode… I clutched the armrests of my chair, my knuckles white with tension, as the skyscraper swayed ominously beneath me. The glass walls of the office building seemed to quiver and shudder, like a living entity in agony. My gaze was fixed on the window in front of me, where a blinding flash had just illuminated the darkening sky. At first, I thought it was just another one of those freak electrical storms that occasionally ravaged our city. But then I saw it - a figure, slumped against the shattered glass, their limbs twisted at unnatural angles. The light from the explosion illuminated their face, and for an instant, I recognized my coworker, Sarah. Her eyes were wide open, frozen in a silent scream. But it wasn't her eyes that haunted me. It was what lay beyond them - a maelstrom of darkness that seemed to seethe and writhe like a living thing. As if whatever had been inside Sarah's body was now bursting free, spilling out into the night air like a noxious black liquid. My mind recoiled in horror as I stared at the carnage unfolding before me. The rest of the office had gone dark, plunging us all into an eerie twilight world. Flickering fluorescent lights cast macabre shadows on the walls, making it seem as though something was moving just out of sight, lurking in the corners. I tried to tear my gaze away, but it was rooted to the scene before me. The figure in Sarah's body began to convulse and twitch, its limbs flailing wildly as if trying to shake off some unseen burden. Its skin had turned a sickly shade of gray, and its mouth hung agape, revealing jagged teeth that seemed to be dripping with blood. A low moan echoed through the building, growing louder with each passing moment. It sounded like nothing human, more like the sound of dry leaves blowing in an endless wind. My heart sank as I realized that this was no ordinary explosion - something had breached our defenses, something ancient and malevolent. The skyscraper swayed again, its movements becoming more erratic and violent. I felt the floor beneath me tremble, as if the very foundations of the building were being torn apart by some unseen force. Panic set in as I scrambled for my phone, desperate to call for help. But my fingers stumbled over the keyboard, unable to find the right buttons. The screen glowed with gibberish code that made no sense to me - it was as though whatever was happening to Sarah had somehow infected our technology itself. As I watched, frozen in terror, Sarah's body began to disintegrate, her limbs melting away like wax in a furnace. Her face contorted into a twisted grimace, and for an instant, I thought I saw her eyes flash open one last time, filled with a deep and abiding hatred. And then she was gone. Replaced by something new, something monstrous. A thing with skin like blackened steel and eyes that burned with an otherworldly green fire. The air around us grew colder, heavy with an unspeakable malevolence that pressed against my eardrums like a physical presence. I could feel it crawling up my legs, spreading across my chest like frostbite. My breath came in ragged gasps as I stared at the horror unfolding before me. I knew we were doomed. We were trapped in a building that was now a portal to some dark realm, a realm where horrors beyond human comprehension lurked in every shadow. And we were the first ones to stumble into this abyss. I tried to scream, but my voice was drowned out by the cacophony of chaos that erupted around me - the wail of sirens that never came, the screams of the damned that echoed through the darkness. The skyscraper shuddered once more, throwing me into the back of my chair. As I looked around frantically for any sign of escape, I realized that we were not alone on the 21st floor. There were others - huddled together in fear, their faces drained of color as they stared at the horror unfolding before them. Some were screaming; others were praying. And still, no one seemed to have noticed what had happened to Sarah... or what had become of her. But I knew the truth. I saw it with my own eyes, saw it writ large in the face of the monster that had taken its place. We were about to become part of something ancient and evil - something that would consume us all, soul and body. The darkness closed in around us, an icy grip that tightened with every passing moment. I closed my eyes, bracing myself for what was to come. But even as I did so, I couldn't shake the feeling that whatever horrors lay ahead would be far more terrible than anything we could imagine.