RPLament-22B-exl2-6bpw

6BPW ExLLamaV2 quant of https://huggingface.co/SvdH/RPLament-22B

Using parquet: https://huggingface.co/datasets/roleplay4fun/pippa

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 as a base.

Models Merged

The following models were included in the merge:

• allura-org/MS-Meadowlark-22B
• Gryphe/Pantheon-RP-1.6.2-22b-Small
• rAIfle/Acolyte-22B
• anthracite-org/magnum-v4-22b

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
parameters:
  int8_mask: true
dtype: bfloat16
models:
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: 0.30
      density: 0.78
  - model: anthracite-org/magnum-v4-22b
    parameters:
      weight: 0.25
      density: 0.66
  - model: allura-org/MS-Meadowlark-22B
    parameters:
      weight: 0.20
      density: 0.54
  - model: rAIfle/Acolyte-22B
    parameters:
      weight: 0.15
      density: 0.42
  - model: Gryphe/Pantheon-RP-1.6.2-22b-Small
    parameters:
      weight: 0.10
      density: 0.42