You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

merge

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 ReadyArt/The-Omega-Directive-M-22B-v1.0 as a base.

Models Merged

The following models were included in the merge:

TheDrummer/Cydonia-22B-v1

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: ReadyArt/The-Omega-Directive-M-22B-v1.0
models:
  - model: ReadyArt/The-Omega-Directive-M-22B-v1.0
    parameters:
      weight: 0.6
  - model: TheDrummer/Cydonia-22B-v1
    parameters:
      weight: 0.4
parameters:
  density: 0.3
tokenizer:
  source: union
chat_template: auto

Downloads last month: 2

Safetensors

Model size

22B params

Tensor type

BF16

Model tree for ReadyArt/Retrograde-Omega-M-22B-v1.0

ReadyArt/The-Omega-Directive-M-22B-v1.0

TheDrummer/Cydonia-22B-v1

Merge model

this model

Quantizations

3 models

Paper for ReadyArt/Retrograde-Omega-M-22B-v1.0

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 30