RichardErkhov/Elfrino_-_PsychoPomp-20B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

PsychoPomp-20B - GGUF

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

Original model description: --- base_model:

• —Elfrino/XwinXtended-20B
• —Undi95/MXLewd-L2-20B library_name: transformers tags:
• —mergekit
• —merge

A merge between an ol' fav: Undi95/MXLewd-L2-20B

and:

An extended XwinLM: Elfrino/XwinXtended-20B

*NOTE: FIRST Merge of XwinXtended and another 20B that finally works and isn't drunk. And it's rather pretty good and coherent, still testing...

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

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
• —Undi95/MXLewd-L2-20B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Undi95/MXLewd-L2-20B
        layer_range: [0, 62]
      - model: Elfrino/XwinXtended-20B
        layer_range: [0, 62]
merge_method: slerp
base_model: Undi95/MXLewd-L2-20B
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: 0.2
dtype: bfloat16