metadata

base_model:
  - nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
  - Sao10K/14B-Qwen2.5-Freya-x1
  - Orion-zhen/Meissa-Qwen2.5-14B-Instruct
  - allura-org/TQ2.5-14B-Aletheia-v1
  - Hasnonname/Qwen2.5-14B-Kebab-v0
  - EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Sao10K/14B-Qwen2.5-Freya-x1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/14B-Qwen2.5-Freya-x1
  - model: allura-org/TQ2.5-14B-Aletheia-v1
    parameters:
      density: 1.00
      weight: 1.00
  - model: Hasnonname/Qwen2.5-14B-Kebab-v0
    parameters:
      density: 1.00
      weight: 1.00
  - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
    parameters:
      density: 0.70
      weight: 0.50
  - model: Orion-zhen/Meissa-Qwen2.5-14B-Instruct
    parameters:
      density: 0.70
      weight: 0.50
  - model: nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
    parameters:
      density: 0.50
      weight: 0.30
merge_method: ties
base_model: Sao10K/14B-Qwen2.5-Freya-x1
parameters:
  normalize: true
dtype: float32