mergekit_config.yml

merge_method: dare_ties

parameters:
  int8_mask: true
  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 # fallback for rest of tensors
  embed_slerp: true

models:
  - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
    # No parameters necessary for base model
  - model: senseable/WestLake-7B-v2
    parameters:
      density: 0.58
      weight: 0.8

base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02

tokenizer_source: model:senseable/WestLake-7B-v2

dtype: bfloat16