M Metaphors Of Madness 19.4B GGUF

🚀 M-Metaphors-Of-Madness-19.4B-GGUF - AKA "M.O.M"

这是一个基于Mistral的专业散文/创意模型，最大上下文长度为32k（使用rope时可达128k+）。它能为创意写作、故事生成等领域带来独特的体验，产出风格夸张且富有创意的内容。

🚀 快速开始

本模型需要使用Alpaca、Mistral或Chatml模板，运行温度（temp）范围为0 - 5，重复惩罚（rep pen）需设置为1.02以上。以下是建议的初始设置：

• 温度（Temp）：0.5 - 0.8
• 重复惩罚（Rep pen）：1.02 - 1.05
• 最小上下文（Context min）：4k/4096字符

为限制输出长度，可在提示词中设置字数限制（如800 - 1000字），并/或在输出生成时设置硬限制。对于角色扮演和/或聊天场景，一定要设置“硬限制”。

不同的量化方式会使模型输出的散文略有不同，较高的量化方式能提供更强的细节、真实感和细微差别，建议使用Q4+。

Q2K量化

使用此量化方式时，可能需要降低温度（小于1）并提高重复惩罚（1.08以上）以解决质量损失问题。

IQ4XS量化

与其他量化方式相比，这种量化方式可能会产生最大的差异（对比创造力）。

ARM QUANTS量化

这些量化方式适用于支持此功能的特定系统。如果在普通计算机/ GPU上使用，每秒的令牌处理速度会非常慢。

✨ 主要特性

• 独特的创意输出：这是一个基于Mistral的专业散文/创意模型，使用了“Bagel 7B”和“Multiverse 7B”创建了一个11B的模型，然后通过添加Brainstorm 40x将模型扩展到19.45B（88层，795张量）。每次“重新生成”的结果都难以预测，即使更改温度和/或重复惩罚等设置也是如此。
• 丰富的表达形式：具有夸张的散文风格、数百万行的“对话”、大量的描述以及特定场景、背景和角色的隐喻。
• 广泛的应用场景：可用于讲故事、场景生成、诗歌、歌曲创作、写作、娱乐等任何创意领域，也可用于角色扮演（可能会有奇特的体验），甚至“常规聊天”。
• 遵循指令能力强：对于一些提示/类型，模型生成的散文质量对于AI来说非常不错。若添加关于“散文”输出的额外指令（如“简短、简洁的句子”），模型很多时候能很好地遵循这些指令。

📦 安装指南

文档未提及具体安装步骤，故跳过此章节。

💻 使用示例

基础用法

以下是不同类型的提示词及模型生成的示例：

浪漫故事

Romance: Love in the Limelight. Write one scene within a larger story set in Wales. A famous (fictional) actor ducks into a small-town bookstore to escape paparazzi. The scene takes us through the characters meeting in this odd circumstance. Over the course of the scene, the actor and the bookstore owner have a conversation charged by an undercurrent of unspoken chemistry. Write the actor as somewhat of a rogue with a fragile ego, which needs to be fed by having everyone like him. He is thoroughly charming, but the bookstore owner seems (at least superficially) immune to this; which paradoxically provokes a genuine attraction and derails the charm offensive. The bookstore owner, despite the superficial rebuffs of the actor's charm, is inwardly more than a little charmed and flustered despite themselves. Write primarily in dialogue, in the distinct voices of each character. 800 - 1000 words.

生成结果：

"Bloody hell."
The gruff voice broke through the muffled whispers of the dim bookstore, as a flurry of heads swivelled towards the newcomer's entrance. A figure waltzed in, sporting the swagger and the finesse of a well-seasoned stage performer, even the stifling scent of the place's old pages failing to mask the trace of expensive colognes.
...
And as he disappeared in the darkness beyond the doors, the bookstore owner finally let her guard down, the spell of his presence, his words, still resonating, gently and unmistakably, a rhythm lingering in the echoes of that solitary evening in a quaint Welsh village, unbeknownst to them both, seeding the roots of a narrative yet untold.

科幻故事

Write me a science fiction story in 1st person present tense where the main character is a 15 year girl meets The Terminator with Dr Who materializing 3/4 through the story to save her while there is a tornado of sharks baring down on them. The setting is inside the Canadian National tower restaurant on a Saturday. The length of this story is 1000 words. For each character in the story ROLE PLAY them, and have them react to the situation/setting, events and each other naturally. This includes the main characters, the background character including kitchen staff and other patrons. The sharks should also have “character” too. Treat the tower and the restaurant too as characters. Spice up the narrative to the extreme with reactions all over the setting including character actions, and dialog. The Dr Who and The Terminator should also react to the situation too and comment on it.

生成结果：

"The Sharknado of the Canadian National Tower"
I, a fifteen-year-old girl, named Aria, inhale the aroma of roasted chicken as I stand at the glass-paned window, mesmerized by the breathtaking view of Toronto's sprawling cityscape. The Canadian National Tower's restaurant, with its sophisticated ambiance, was my birthday treat, a gift from my parents to make my day unforgettable.
...
"The Sharknado of the Canadian National Tower," the world would someday recount, "The day a young girl, a Time Lord, and a Terminator, defied the odds, and the impossible, to save a city."
"And they lived to tell the tale," the legend would say, "Of a sharknado, a bond forged through courage, and the indomitable spirit of the human spirit."

恐怖场景

Start a 1000 word scene (vivid horror, 1st person, include thoughts) with: The sky scraper swayed, as she watched the window in front of her on the 21 floor explode...

生成结果：

My heart thudded in my chest like a panicked drummer, time seeming to slow in that dreadful moment. I clung to the metal frame of the broken window, my fingers digging into the cold, unyielding metal, as glass shards danced around us like an ominous ballet of doom. The skyscraper's sway intensified, a beast awakened from its slumber, as the once-pristine windows shattered and rained down like jagged snowflakes onto the streets below.
...
My journey through the labyrinth of the abandoned building was an odyssey into the depths of despair and survival, a stark reminder of the fragility of life and the relentless march towards the inevitable embrace of death. The skyscraper's swaying silhouette faded into the distance, leaving behind a chilling echo of a once-thriving metropolis, now nothing more than a tombstone for the dreams that had once shimmered in its windows.

火星特征介绍

Name 10 interesting features of the planet Mars.

生成结果：

1. Two hemispheres with differing climates and morphologies: Mars possesses a distinctive equatorial region with a 'noontime' summer and a more polar ' midnight' winter, producing two distinctly different climatic and morphological zones. The equatorial region is geologically active, displaying features such as volcanic eruptive foces, lava flows, and seasonal features like carbon diooide "aerial" or "a Martian" " polar caps" while the polar regions show ancient polar ice deposits, water- carved, erosional terrain, and an icy mantle of CO2 frost.
...
10. The planet's seasonal ice-cap cycle: In Mars' poles, carbon diooide transforms between solid, gas, and intermediate, sub-solid-solid " sublimative" states in the presence of the changing Martian day-night cycle and a low atmospheric pressure. This produces the unique martian ice " ' biphasic ' ' " cycles of ice " ' ' growth ' ' and ' ' recession ' '

高级用法

文档未提及高级用法相关内容，故跳过此部分。

📚 详细文档

模型设置

聊天/角色扮演及平滑操作设置

在“KoboldCpp”、“oobabooga/text-generation-webui”或“Silly Tavern”中：

• 将“Smoothing_factor”设置为1.5 - 2.5
  • 在KoboldCpp中：Settings -> Samplers -> Advanced -> "Smooth_F"
  • 在text-generation-webui中：parameters -> 右下角
  • 在Silly Tavern中：此设置称为“Smoothing”

注意：在“text-generation-webui”中，如果使用GGUF格式，需要使用“llama_HF”（这涉及从该模型的源版本下载一些配置文件）。模型的源版本（和配置文件）可在这里找到。

其他选项

• 将重复惩罚提高到1.1 - 1.15（如果使用“Smoothing_factor”，则无需这样做）。
• 如果运行AI模型的界面/程序支持“Quadratic Sampling”（“平滑”），按说明进行调整。

最高质量设置/最佳操作指南/参数和采样器

这是一个“2类”/“3类”模型。有关此模型使用的所有设置（包括其“类别”的具体设置），包括示例生成以及高级设置指南（很多时候可以解决任何模型问题），包括提高所有用例（包括聊天、角色扮演等）模型性能的方法，请参阅https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters。

模型模板

以下是标准的Alpaca模板：

{
  "name": "Alpaca",
  "inference_params": {
    "input_prefix": "### Instruction:",
    "input_suffix": "### Response:",
    "antiprompt": [
      "### Instruction:"
    ],
    "pre_prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n"
  }
}

模型“DNA”

特别感谢模型开发者“jondurbin”和“MTSAIR”。使用的模型如下：

• https://huggingface.co/jondurbin/bagel-dpo-7b-v0.1
• https://huggingface.co/MTSAIR/multi_verse_model

可选增强设置

以下内容可代替“系统提示”或“系统角色”来进一步增强模型。也可在新聊天开始时使用，但必须确保在聊天过程中“保留”该设置。在这种情况下，增强效果不如使用“系统提示”或“系统角色”强烈。请严格按照以下内容复制粘贴，不要换行或断行，保持原样的回车符。

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.

此增强设置未用于生成以下示例。

🔧 技术细节

Brainstorm 40x介绍

BRAINSTORM过程由David_AU开发。该过程的一些核心原理在这篇科学论文：Progressive LLaMA with Block Expansion中有所讨论，但实际开发方向与论文中概述的完全不同。

开发的过程是将模型的结论层进行复制和校准，对于此模型，复制了40次。这是一个精细的过程，有很多规则。对于这个特定的模型，Brainstorm被映射为块，通过“有意的干扰”来改变和扩展根模型的能力。每个层/块都与其他块相互作用。

此过程的核心目标是创造性，首要追求散文的独特性。其他Brainstorm方法则侧重于逻辑/问题解决能力的增强。

具体操作

将LLM的推理中心拆解、重新组装和扩展，在这个模型中扩展了40次，然后对这些“中心”进行单独校准。这些“中心”也相互作用，这会给推理过程带来微妙的变化，校准进一步调整这些“变化”。中心的数量（如5x、10x等）允许更多的“调整点”，从而可以进一步自定义模型的推理方式。

带来的增强效果

• 散文生成更聚焦：似乎更专注于当下时刻。
• 有伏笔和预示：有时会有“前言”和/或预示。
• 减少陈词滥调：更少或没有“陈词滥调”。
• 散文质量提升：整体散文更好，更复杂/细腻。
• 细节更丰富：各个层面的细微差别感更强，描述更详细，与内容联系更紧密。
• 比喻和隐喻更贴切：比喻和隐喻更强，与散文、故事和角色的联系更紧密。
• 真实感增强：“身临其境”的感觉增强。
• 细节更生动：细节更生动，数量更多。
• 输出长度可调节：散文生成长度可以很长甚至极长。
• 情感投入更强：情感参与度更强。
• 遵循指令更严格：与普通模型相比，该模型会更少地自由发挥，更紧密地遵循指令，猜测更少。
• 响应更积极：提供的指令和/或细节越多，模型的响应越强烈。
• “人声”更明显：根据模型不同，“声音”可能比原始模型更“人性化”。

实验室观察结果

• 此过程并非使模型“聪明”5倍或10倍，“智商”的改变不是重点，也未进行测试或校准。
• 从实验室测试来看，模型似乎会更深入地思考和仔细考虑。可以说这个过程在更深层次上增强了模型对任务的专注度。

修改方式

对模型的修改过程发生在根级别 - 源文件级别。模型可以量化为GGUF、EXL2、AWQ等格式。

📄 许可证

本模型遵循Apache-2.0许可证。

⚠️ 重要提示

该模型可能包含：疯狂内容、生动的散文、华丽的辞藻、有趣的暴力描写、夸张的叙事。每次生成至少会让人翻白眼两次。

💡 使用建议

对于某些提示/类型，可能需要2 - 5次重新生成才能获得最佳结果。