RichardErkhov/Elfrino_-_AndroidPrincess-20B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

AndroidPrincess-20B - GGUF

• —Model creator: https://huggingface.co/Elfrino/
• —Original model: https://huggingface.co/Elfrino/AndroidPrincess-20B/

Original model description: --- base_model:

• —Elfrino/XwinXtended-20B
• —seb-c/Psydestroyer-20B library_name: transformers tags:
• —mergekit
• —merge

NOTES: LOOKS PROMISING SO FAR..... IN TESTING......*

*Some findings: Articulate, long flowy sentences and can be pushed to high temps. Lacks the zany outlandish creativity of PsymedRP-20B or Xwin-MLewd-20B but it's still a solid story weaver..*

##################################################################################################################

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• —Elfrino/XwinXtended-20B
• —seb-c/Psydestroyer-20B

Configuration

The following YAML configuration was used to produce this model:

NEXT TRIAL: make WizardLM into a 20B and SLERP it with XwinXtended? maybe....



slices:
  - sources:
      - model: seb-c/Psydestroyer-20B
        layer_range: [0, 62]
      - model: Elfrino/XwinXtended-20B
        layer_range: [0, 62]
merge_method: slerp
base_model: seb-c/Psydestroyer-20B
parameters:
  t:
    - filter: self_attn
      value: [0.8, 0.8, 0.9, 0.7, .8]
    - filter: mlp
      value: [.8, 0.8, 0.9, 0.8, .7]
    - value: 0.3369
dtype: bfloat16