Nitral-Archive/Captain-Eris_Rebased

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Nitral-Archive/Captain-Eris-Violet-12B-GRPO + Nitral-Archive/Nera_Noctis-r64-test_train-lora-12B
• Nitral-AI/Wayfarer_Eris_Noctis-12B + Nitral-Archive/meme-12b-lora-e2

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Nitral-Archive/Captain-Eris-Violet-12B-GRPO+Nitral-Archive/Nera_Noctis-r64-test_train-lora-12B
        layer_range: [0, 40]
      - model: Nitral-AI/Wayfarer_Eris_Noctis-12B+Nitral-Archive/meme-12b-lora-e2
        layer_range: [0, 40]
merge_method: slerp
base_model: Nitral-Archive/Captain-Eris-Violet-12B-GRPO+Nitral-Archive/Nera_Noctis-r64-test_train-lora-12B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.420
dtype: bfloat16