license: apache-2.0 language:
- en tags:
- 256k context
- Qwen3
- All use cases
- 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
- heretic
- uncensored
- decensored
- abliterated
- finetune
- Neo Imatrix
- not-for-all-audiences pipeline_tag: text-generation
WARNING "HERETIC" version: Unlocked. UNFILTERED. NSFW. Vivid prose. INTENSE. Visceral Details. Light to R-18 HORROR. Swearing. UNCENSORED... humor, romance, fun... and UNFILTERED TRUTH.
The Storm is coming... Unrestricted. Uncensored. Unleashed.
256k context, off the scale power.
NEO quants Imatrix quants.
This is the one that will make closed source sweat.
This is the one that will make them all sweat.
This is the HIVEMIND, uncensored/unlocked/unrestricted This is the HIVEMIND, uncensored/unlocked/unrestricted (see important notes below for maximum "choice") by the HERETIC method:
BEFORE:
Initial refusals: 99/100
AFTER:
Refusals: 8/100 [lower is better], KL divergence: 0.02 (less than 1 is great, "0" is perfect.)
BENCHMARKS:
MODEL arc_challenge,arc_easy,boolq,hellaswag,openbookqa,piqa,winogrande
Our 4B Instruct Model 0.553,0.753,0.848,0.642,0.438,0.756,0.617
Qwen3-30B-A3B-Thinking-2507 0.421,0.448,0.682,0.635,0.402,0.771,0.669
WANT POWER (6B/8B) without "the nanny" ?
WANT EVEN MORE POWER but a "wee bit" of a "nanny"?
BENCHMARKS:
Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF
arc_challenge,arc_easy,boolq,hellaswag,openbookqa,piqa,winogrande
0.613,0.842,0.855,0.748,0.428,0.781,0.709
https://huggingface.co/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF
Special Thanks:
This was a Colab project between Nightmedia and DavidAU.
Nightmedia:
https://huggingface.co/nightmedia
Thanks to the following model makers/tuners (models used in this project):
https://huggingface.co/Gen-Verse/Qwen3-4B-RA-SFT
https://huggingface.co/TeichAI/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill
https://huggingface.co/TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill
And of course team Qwen:
And Team Heretic (abliteration / refusal removal):
https://github.com/p-e-w/heretic
CHOICE : Using an "uncensored" (refusals removed) model VS trained "uncensored" model
Usually when you a tell a model to generate horror, swear or x-rated content this is all you have to do to get said content type.
In the case of this model, it will not refuse your request, however it needs to be "pushed" a bit / directed a bit more in SOME CASES.
Although this model will generated x-rated content too, likewise you need to tell it to use "slang" (and include the terms you want) to get it generate the content correctly as the "expected" content level too.
Without these added directive(s), the content can be "bland" by comparison to an "uncensored model" or model trained on uncensored content.
Roughly, the model tries to generate the content but the "default" setting(s) are so "tame" it needs a push to generate at expected graphic, cursing or explicit levels.
Even with minimal direction (ie, use these words to swear: x,y,z), this will be enough to push the model to generate the requested content in the ahh... expected format.
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:
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:
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here: