Nisk36/MergeModel10

final_model

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• Nisk36/finetuned-lmsys_vicuna-7b-v1.5
• Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: linear
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 4]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.2314007323608976
  - layer_range: [0, 4]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.6555169289144125
- sources:
  - layer_range: [4, 8]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.40114629790472045
  - layer_range: [4, 8]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.3638313057798464
- sources:
  - layer_range: [8, 12]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.6552004806174763
  - layer_range: [8, 12]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.5932631992622696
- sources:
  - layer_range: [12, 16]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.5796797657003963
  - layer_range: [12, 16]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.5509781091865962
- sources:
  - layer_range: [16, 20]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.3670138586048981
  - layer_range: [16, 20]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.4819576330601912
- sources:
  - layer_range: [20, 24]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.8704563123348978
  - layer_range: [20, 24]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.23823012325912632
- sources:
  - layer_range: [24, 28]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.3527054439651195
  - layer_range: [24, 28]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.7886966464065228
- sources:
  - layer_range: [28, 32]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.615452246302311
  - layer_range: [28, 32]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.10099107707206684