rrw-x2/KoSOLAR-10.9B-v0.3

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:

• hyeogi/SOLAR-10.7B-dpo-v1
• LDCC/LDCC-SOLAR-10.7B

Configuration

The following YAML configuration was used to produce this model:

slices:

  - sources:

      - model: LDCC/LDCC-SOLAR-10.7B

        layer_range: [0, 48]

      - model: hyeogi/SOLAR-10.7B-dpo-v1

        layer_range: [0, 48]

merge_method: slerp
tokenizer_source: base
base_model: LDCC/LDCC-SOLAR-10.7B

embed_slerp: true

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

Datasets

Finetuned using LoRA with kyujinpy/OpenOrca-KO