Edit model card

Experimental Builds in F32 and Imatrix upscaling for 20B model.

Mix of req quant / imatrix quants.

These are attempts to further improve F32 upscales projects noted below.

Use at own risk as output may be NSFW.

Related to F32 Master Upscale project:

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

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

In part related to:

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

https://huggingface.co/DavidAU/Fimbulvetr-11B-Ultra-Quality-plus-imatrix-GGUF

Downloads last month
20
GGUF
Model size
20.6B params
Architecture
llama

4-bit

5-bit

6-bit

Inference Examples
Inference API (serverless) is not available, repository is disabled.

Collection including DavidAU/Psyonic-Cetacean-EXP