Ultra High Quality - 20B Dark Forest Version 2.0 - 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 two original versions of "Dark Forest 20B", this is an upscale of the second version.
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.
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 ]
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: