DavidAU/DarkForest-20B-V3-Ultra-Quality-GGUF

Ultra High Quality - 20 B Dark Forest Version 3.0 - 32 bit upscale

Fully rebuilt from master files, including full merge(s) to maintain full 32 bit precision right up until it is compressed into GGUF files which results on a top to bottom upgrade.

The result is superior performance in instruction following, reasoning, depth, nuance and emotion.

NOTE: There are three original versions of "Dark Forest 20B", this is an upscale of the third version, with links below to 1st and 2nd versions also upscaled.

On average this means a q4km operates at Q6 levels and Q6 and Q8 exceeds original model full precision performance.

Perplexity drop (lower is better) is close to 10% (over 752 points for q4km) for all quants.

That means precision has been enhanced for all 20 billion parameters which affects "brain density" / "function", instruction following and output quality.

Imatrix quants to follow shortly.

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.

For more details, including a list of enhancements see our other 32 bit upscale of "Space Whale 20B" rebuild here:

[ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF ]

For Version 1 of Dark Forest Ultra Quality 32 bit upscale please go here:

[ https://huggingface.co/DavidAU/Dark-Forest-V1-Ultra-Quality-20b-GGUF ]

For Version 1 of Dark Forest Ultra Quality 32 bit upscale please go here:

[ https://huggingface.co/TeeZee/DarkForest-20B-v2.0 ]

Special thanks to "TEEZEE" for making a both fantasic models of "Dark Forest".

Info from the original model card:

Warning: This model can produce NSFW content!

Results:

- main difference to v1.0 - model has much better sense of humor.
- produces SFW nad NSFW content without issues, switches context seamlessly.
- good at following instructions.
- good at tracking multiple characters in one scene.
- very creative, scenarios produced are mature and complicated, model doesn't shy from writing about PTSD, menatal issues or complicated relationships.
- NSFW output is more creative and suprising than typical limaRP output.
- definitely for mature audiences, not only because of vivid NSFW content but also because of overall maturity of stories it produces.
- This is NOT Harry Potter level storytelling.

For original model spec and information please visit:

[ https://huggingface.co/TeeZee/DarkForest-20B-v3.0 ]

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:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

---

Special Thanks:

---

Special thanks to all the following, and many more...

All the model makers, fine tuners, mergers, and tweakers:

• Provides the raw "DNA" for almost all my models.
• Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).

Huggingface [ https://huggingface.co ] :

• The place to store, merge, and tune models endlessly.
• THE reason we have an open source community.

LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :

• The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
• Imatrix, Quantization, and other tools to tune the quants and the models.
• Llama-Server : A cli based direct interface to run GGUF models.
• The only tool I use to quant models.

Quant-Masters: Team Mradermacher, Bartowski, and many others:

• Quant models day and night for us all to use.
• They are the lifeblood of open source access.

MergeKit [ https://github.com/arcee-ai/mergekit ] :

• The universal online/offline tool to merge models together and forge something new.
• Over 20 methods to almost instantly merge model, pull them apart and put them together again.
• The tool I have used to create over 1500 models.

Lmstudio [ https://lmstudio.ai/ ] :

• The go to tool to test and run models in GGUF format.
• The Tool I use to test/refine and evaluate new models.
• LMStudio forum on discord; endless info and community for open source.

Text Generation Webui // KolboldCPP // SillyTavern:

• Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
• Sillytavern [ https://github.com/SillyTavern/SillyTavern ] can be used with LMSTudio [ https://lmstudio.ai/ ] , TextGen [ https://github.com/oobabooga/text-generation-webui ], Kolboldcpp [ https://github.com/LostRuins/koboldcpp ], Llama-Server [part of LLAMAcpp] as a off the scale front end control system and interface to work with models.