mergekit-community/MN-Sappho-k-12B

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/MN-Sappho-j-12B as a base.

Models Merged

The following models were included in the merge:

• anthracite-org/magnum-v2.5-12b-kto
• mergekit-community/MN-Sappho-e-12B
• Azazelle/MN-Halide-12b-v1.0
• inflatebot/MN-12B-Mag-Mell-R1 + XeroCodes/aurora-12b
• mergekit-community/MN-Sappho-b-12B + jtatman/mistral_nemo_12b_reasoning_psychology_lora
• Khetterman/AbominationScience-12B-v4
• mistralai/Mistral-Nemo-Instruct-2407

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/MN-Sappho-j-12B
models:
  - model: mergekit-community/MN-Sappho-e-12B
  - model: mergekit-community/MN-Sappho-b-12B+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: Khetterman/AbominationScience-12B-v4
  - model: anthracite-org/magnum-v2.5-12b-kto
  - model: inflatebot/MN-12B-Mag-Mell-R1+XeroCodes/aurora-12b
  - model: Azazelle/MN-Halide-12b-v1.0
  - model: mistralai/Mistral-Nemo-Instruct-2407