metadata

base_model:
  - EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
  - anthracite-org/magnum-v4-72b
library_name: transformers
tags:
  - mergekit
  - merge

SteyrCannon-Qwen2.5-72b

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

Thanks to Auri for the suggestion!

This recipe follows closely to StarCannon-v3 but with the desnity for magnum-v4 reduced even further. Magnum-v4 feels a bit overcooked.

Quants & Hosts

Merge Details

Merge Method

This model was merged using the TIES merge method using EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1 as a base.

Models Merged

The following models were included in the merge:

anthracite-org/magnum-v4-72b
EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: anthracite-org/magnum-v4-72b
    parameters:
      density: 0.25
      weight: 0.5
  - model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
    parameters:
      density: 0.75
      weight: 0.5

merge_method: ties
base_model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
parameters:
  normalize: true
dtype: bfloat16