mergekit_config.yml

# slices:
#   - sources:
#       - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 # 21 Layers
#         layer_range: [0, 21]
#       - model: microsoft/Phi-3-mini-4k-instruct # 31 Layers
#         layer_range: [10, 31]
# merge_method: slerp
# base_model: microsoft/Phi-3-mini-4k-instruct
# parameters:
#   t:
#     - filter: self_attn.o_proj
#       value: 0.5
#     - filter: self_attn.qkv_proj
#       value: 0.5
#     - filter: mlp.down_proj
#       value: 0.5
#     - filter: input_layernorm
#       value: 0.5
#     - filter: post_attention_layernorm
#       value: 0.5
#     - filter: embed_tokens
#       value: 0.5
#     - value: 0
# dtype: bfloat16

slices:
  - sources:
      - model: mistralai/Mistral-7B-Instruct-v0.2 # 21 Layers
        layer_range: [0, 31]
      - model: meta-llama/Meta-Llama-3.1-8B-Instruct # 31 Layers
        layer_range: [0, 31]
merge_method: slerp
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
parameters:
  t:
    - filter: self_attn
      value: 0.5
    - filter: mlp
      value: 0.5
    - value: 0.5
dtype: bfloat16