README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - Gille/StrangeMerges_32-7B-slerp
  - yam-peleg/Experiment26-7B

shadow-clown-7B-slerp

shadow-clown-7B-slerp is a DARE merge of the following models using mergekit:

• Gille/StrangeMerges_32-7B-slerp
• yam-peleg/Experiment26-7B

See the paper Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch for more on the method.

🧩 Configuration

slices:
  - sources:
      - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
        layer_range: [0, 32]
      - model: MSL7/INEX12-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
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

slices:
  - sources:
      - model: liminerity/M7-7b
        layer_range: [0, 32]
      - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/M7-7b
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


slices:
  - sources:
      - model: ammarali32/multi_verse_model
        layer_range: [0, 32]
      - model: liminerity/merge
        layer_range: [0, 32]
merge_method: slerp
base_model: ammarali32/multi_verse_model
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


slices:
  - sources:
      - model: Gille/StrangeMerges_32-7B-slerp
        layer_range: [0, 32]
      - model: yam-peleg/Experiment26-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: Gille/StrangeMerges_32-7B-slerp
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