--- license: apache-2.0 language: - en tags: - 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 prose - vivid writing - fiction - roleplaying - bfloat16 - swearing - rp - llama3.1 - context 128k - Context 131,072 - enhanced quants - max quants - maxcpu quants - horror - mergekit pipeline_tag: text-generation --- (quants uploading, model card / examples to be updates/added.)

Llama-3.1-128k-Dark-Planet-Uncensored-8B-GGUF

It is a LLama 3.1 model, max context of 128k, with additional de-censoring as well as additional steps to improve generation. 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 Llama 3 template and/or "Command-R" template. Example outputs below. Model Notes: - Detail, prose and fiction writing abilities are significantly increased vs L3 Instruct. - 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, 1.05+ 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". The Imatrix versions of this model have even lower perplexity (1/2 level of magnitude lower than this model, 1 full level of magnitude lower than LLama3 Instruct) then both this model and Llama3 Instruct and enhanced output. Dark Planet Versions: Dark Planet 8B SpinFire, now with Llama 3.1 and uncensored: [ https://huggingface.co/DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B-GGUF ] The Monster Darkest Planet 16.5B L3: Drastically increase detail, quality, and raw creative power over Dark Planet 8B using DavidAu's Brainstorm 40x augmentation. [ https://huggingface.co/DavidAU/L3-DARKEST-PLANET-16.5B-GGUF ] NEO IMATRIX quants are here: [ https://huggingface.co/DavidAU/L3-Dark-Planet-8B-NEO-Imatrix-GGUF ] NEO IMATRIX - DARK HORROR quants: [ https://huggingface.co/DavidAU/L3-Dark-Planet-Horror-City-8B-NEO-Imatrix-GGUF ] F32 Version (mastered from float32 source files): [ https://huggingface.co/DavidAU/L3-Dark-Planet-Ring-World-8B-F32-GGUF ] I suggest downloading quant(s) of both "Bloat16" and "Float32" versions of this model for your use case(s). The Float32 version has increased detail, "stays in the moment", and slightly higher creativity. However their "character" is different from one another too. Version 2 - Eight Orbs Of Power is here: [ https://huggingface.co/DavidAU/L3-Dark-Planet-8B-V2-Eight-Orbs-Of-Power-GGUF ] Template: This is a LLAMA 3 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|>"
    ]
  }
}
Model "DNA": Special thanks to the incredible work of the model makers "SAO10K", "NEVERSLEEP" and "HASTAGARAS". Models used: [ https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2] [ https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS ] [ https://huggingface.co/Hastagaras/Jamet-8B-L3-MK.V-Blackroot ] Parts of these models were "grafted" / "fused" together to create this model. 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 to 2.5 : 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 Q4_K_M, "temp=.8" (unless otherwise stated), minimal parameters and "LLAMA3" template. Model has been tested with "temp" from ".1" to "5". Below are the least creative outputs, prompt is in BOLD. --- WARNING: NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED. ---