Triangle104/Ministrudel-19B

Merge

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

Merge Details

Base model for further finetuning.

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• cognitivecomputations/Dolphin3.0-R1-Mistral-24B
• ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
        layer_range: [0, 32]
      - model: cognitivecomputations/Dolphin3.0-R1-Mistral-24B
        layer_range: [0, 32]
merge_method: slerp
base_model: cognitivecomputations/Dolphin3.0-R1-Mistral-24B
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: 0.5
dtype: bfloat16