Nohobby/Karasik-22B-v0.1

Karasik 0.1

Overview

Somewhat experimental merge of some Mistral Small models.

Quants

Q5_K_M

More coming soon

Merge Details

Merge Method

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

Models Merged

The following models were included in the merge:

• rAIfle/Acolyte-22B
• byroneverson/Mistral-Small-Instruct-2409-abliterated
• DazzlingXeno/Cydonian-Gutenberg

Configuration

The following YAML configuration was used to produce this model:

base_model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
parameters:
  epsilon: 0.04
  lambda: 1.05
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
models:
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: [0.2, 0.3, 0.2, 0.3, 0.2]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
  - model: rAIfle/Acolyte-22B
    parameters:
      weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
      density: [0.6, 0.4, 0.5, 0.4, 0.6]
  - model: byroneverson/Mistral-Small-Instruct-2409-abliterated
    parameters:
      weight: [0.208, 0.139, 0.139, 0.139, 0.208]
      density: [0.7]
  - model: DazzlingXeno/Cydonian-Gutenberg
    parameters:
      weight: [0.33]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]