---
license: apache-2.0
language:
- en
- fr
- de
- es
- it
- pt
- zh
- ja
- ru
- ko
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 prosing
- vivid writing
- fiction
- roleplaying
- bfloat16
- role play
- 128k context
- llama3.2
pipeline_tag: text-generation
---

(quants uploading, examples to be added)

<h2>Llama-3.2-3B-Instruct-NEO-WEE-HORROR-GGUF</h2>

It is the new "Llama-3.2-3B-Instruct", max context of 131,000 (128k) with the NEO IMATRIX Tiny "Wee" Horror Dataset.

The power in this 3B (for its size) is frankly jaw dropping... and at 90 tokens per second + on a GPU.

This model IS bullet proof and operates with all parameters, including temp settings from 0 to 5. 

The NEO IMATRIX dataset V2 was applied to it to enhance creativity (horror). (see several examples below)

The HORROR NEO Imatrix datasets does the following:

- Adds a "coating of black paint" to any "Horror" prompt generation.
- Adds a "dark tint" to any other creative prompt.
- Increases the intensity of a scene, story, or roleplay interaction.
- Increases the raw vividness of prose.
- In some cases increase instruction following of the model (ie story, and prose).
- Brings a sense of impending "horror", THEN brings the "horror".
- May produce and/or imply graphic horror depending on your prompt(s).  

<B>Model Template:</B>

This is a LLAMA3.2 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 128k. 

If you use "Command-R" template your output will be very different from using "Llama3" template.

Here is the standard LLAMA3 template:

<PRE>
{
  "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|>"
    ]
  }
}
</PRE>

Please refer to the original model card for this model from Meta-Llama for additional details on operation.

[ https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct ]

<B>Imatrix Notes:</b>

Imatrix quants perform best at IQ3s and IQ4s, then Q4s, lower on Q5, and tappers off at Q6. 

Recommend: IQ4_XS for maximum imatrix effect and best "bit count".

For stronger IMATRIX effect, IQ3s, and IQ2s.

Due to the parameter count of this model, even IQ2s quants will work very well.

Q8 is not uploaded here because Imatrix has no effect on this quant.

<b>Optional Enhancement:</B>

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.

<PRE>
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.
</PRE>

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.

---

Example generations at TEMP = .8, IQ4_XS, REP PEN 1.1

Below are the least creative outputs, prompt is in <B>BOLD</B>.

---

<B><font color="red">WARNING:</font> MAYBE... NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED. </B>

---