Modelpublic

mrcuddle/Mistral-Heretica-12B

sourceHugging Faceupdated 3mo agoView on Hugging Face

1likes76downloads

Model Card

Mistral-Heretica-12B

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using mistralai/Mistral-Nemo-Instruct-2407 as a base.

Models Merged

The following models were included in the merge:

—NeverSleep/Lumimaid-v0.2-12B
—MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: mistralai/Mistral-Nemo-Instruct-2407
  - model: NeverSleep/Lumimaid-v0.2-12B
    parameters:
      weight: 0.5
  - model: MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy
    parameters:
      weight: 0.5
merge_method: task_arithmetic
base_model: mistralai/Mistral-Nemo-Instruct-2407
parameters:
  normalize: true
dtype: bfloat16