mergekit_config.yml

merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-v0.1-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: stabilityai/japanese-stablelm-base-gamma-7b
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: DataPilot/ArrowPro-7B-KillerWhale
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: ArrowPro-7B-KillerWhale-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: nitky/RP-7b-instruct
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: RP-7b-instruct-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-Instruct-v0.3
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: tokyotech-llm/Swallow-MS-7b-instruct-v0.1
    parameters:
      weight: 0.8
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight: -0.8
  - model: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: Mistral-7B-v0.1-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-alpha
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: ArrowPro-7B-KillerWhale-VE-Swallow-MS # include Mistral-7B-Instruct-v0.3
    parameters:
      weight: 0.8
  - model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-beta
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: RP-7b-instruct-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
    parameters:
      weight: -0.8
  - model: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: Mistral-7B-v0.1-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-gamma
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: Oumuamua-7b-instruct-alpha
  - model: Oumuamua-7b-instruct-beta
  - model: Oumuamua-7b-instruct-gamma
dtype: bfloat16
name: Oumuamua-7b-instruct