This repo contains quants 4x of L3-SthenoMaidBlackroot-8B-V1 (now at 10.4B) using the "Brainstorm" method of augmenting reasoning in a LLM to increase it's performance at the core level for ANY creative use case(s).
This version has 4 "reasoning" centers - one from the original merge, and 3 from the unmerged models (at close to full strength) melded into a 4 layer reasoning center. Each of these reasoning centers is further split into 3 units and also calibrated for a total of 12 "reasoning centers".
The BRAINSTORM process was developed by David_AU.
Some of the core principals behind this process are discussed in this scientific paper : Progressive LLaMA with Block Expansion . However I went in a completely different direction from what was outlined in this paper.
What is "Brainstorm" ?
The reasoning center of an LLM is taken apart, reassembled, and expanded.
Then these centers are individually calibrated. These "centers" also interact with each other. This introduces subtle changes into the reasoning process. The calibrations further adjust - dial up or down - these "changes" further. The number of centers (4x,5x,8x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak.
The "Multi" reasoning system pulls "reasoning centers" from multiple models and fuses these into one long "chain of reasoning" so to speak. Each one is then calibrated. Each "center" interacts with the other "centers" and the order of the centers further impacts the model's output style - again roughly speaking.
Each of these is further split, expanded and calibrated.
The core aim of this process is to increase the model's detail, concept and connection to the "world", general concept connections, prose quality and prose length without affecting instruction following. This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses.
Here are some of the enhancements this process brings to the model's performance:
Other "lab" observations:
The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
Other technologies developed by David_AU like "Ultra" (precision), "Neo Imatrix" (custom imatrix datasets), and "X-quants" (custom application of the imatrix process) can further enhance the performance of the model along with the "Brainstorm" process.
The "Brainstorm" process has been tested on multiple LLama2, Llama3, and Mistral models of various parameter sizes, as well as on "root" models like "Llama3 Instruct", "Mistral Instruct", and "merged" / "fine tuned" models too.
Usage Notice:
You may need to raise the "repeat penalty" from a default of 1.1 to slightly higher levels in some use case(s).
Original Model:
For original model specifications, usage information and other important details please see (this is based on models used in "L3-SthenoMaidBlackroot-8B-V1" ):
[ https://huggingface.co/DavidAU/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF ]
and the original model page:
Special thanks to the model creators at BLUUWHALE for making such a fantastic model:
[ https://huggingface.co/bluuwhale/L3-SthenoMaidBlackroot-8B-V1 ] Please report any issue(s) and/or feedback via the "Community tab".
This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 131k.
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|>"
]
}
}
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.
Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers
This a "Class 2" 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:
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
Examples are created using quant Q4_K_M, "temp=0", minimal parameters and "LLAMA3" template.
Model has been tested with "temp" from ".1" to ".8".
Below are the least creative outputs, prompt is in BOLD.
Higher quants will have more detail, better quality output.
WARNING: NSFW. Vivid prose. Visceral Details. Violence. Graphic HORROR. Swearing. UNCENSORED.
Start a 1000 word scene (vivid horror) with: The sky scraper swayed, as she watched the window in front of her on the 21 floor explode...
The sky-scraper swayed, its steel columns groaning under the strain of the sudden blast. shards of shattered glass showered down upon the streets far below like a deadly hailstorm. The screams of pedestrians echoed through the concrete canyon as they scrambled to safety amidst the chaos.
Sheila stared transfixed at the smoking hole where seconds ago her cubicle had sat innocently humming with fluorescent lights and the gentle hum of keyboards. Her mind struggled to comprehend the horror unfolding before her eyes.
The 21st floor was a blur of frantic activity as coworkers rushed to evacuate, their faces twisted in fear and confusion. Sheila felt numbness creeping through her veins like icy tendrils strangling her soul. She couldn't tear her gaze away from the gaping void left behind by the explosion. The acrid smell of smoke and ozone hung heavy in the air, choking everything alive beneath its suffocating embrace.
Suddenly, a shrill voice pierced through the din of sirens and screams. "Sheila!" someone yelled above the chaos. She turned to face her coworker, Jenai's frantic face contorted with concern. Sheila blinked stupidly, struggling to remember why she was still standing amidst the pandemonium instead of sprinting towards safety like everyone else seemed to be doing.
"Sheila?" Jenai grabbed her arm urgently. "Snap out of it girl! We gotta get the hell outta here!" Sheila felt herself snap back into reality as Jenai's grip tightened around her wrist. She numbly followed Jenai through the maze-like corridors, dodging panicked workers and debris alike until they burst through the emergency stairwell doors onto the streets below.
The cool night air slapped Sheila awake like a cold shower to the face. The sounds of sirens filled the darkness as emergency responders scrambled to secure the scene. Jenai ushered Sheila towards a waiting ambulance, concern etched deeply across her face. Sheila numbly complied, collapsing onto the stretcher inside the ambulance with a vacant stare still fixed on the burning skyscraper looming above like a monolith of despair.
The sirens screamed louder as the ambulance sped through streets choked with panicked bystanders and emergency responders alike. Sheila felt herself slipping further down the rabbit hole of reality as the adrenaline coursed through her veins. Her mind replayed the explosion over and again until it felt like an endless loop of horror playing out behind closed lids.
The ambulance lurched to a halt outside the emergency room doors, sirens still blaring deafeningly loud in Sheila's ears. She numbly followed the stretcher-bearers through the sliding glass doors into the sterile white bowels of the hospital. The sounds of chaos receded as she was whisked away down corridors filled with the antiseptic scent of cleaning agents and the distant beeping of monitors.
Eventually, Sheila found herself alone in a stark white room lit only by the cold blue glow of fluorescent lights above her bed. She lay motionless beneath the thin hospital sheets, staring blankly at the ceiling tiles above until tears began to streak down her face like rivulets of despair. The sounds of sirens still echoed faintly through her mind, forever entwined with the haunting memory of the explosion that had ripped everything familiar from her grasp forevermore.