mergekit-community/mergekit-model_stock-qdhvbzt

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mergekit-community/mergekit-model_stock-kvunitr + jtatman/mistral_nemo_12b_reasoning_psychology_lora as a base.

Models Merged

The following models were included in the merge:

• mergekit-community/mergekit-ties-mwxogrc
• mergekit-community/mergekit-model_stock-lgpoodo

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/mergekit-model_stock-kvunitr+jtatman/mistral_nemo_12b_reasoning_psychology_lora
models:
  - model: mergekit-community/mergekit-model_stock-kvunitr+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: mergekit-community/mergekit-model_stock-lgpoodo
  - model: mergekit-community/mergekit-ties-mwxogrc
    parameters:
      weight: 0.5

parameters:
  normalize: true