BlokeNeural

BlokeNeural is a merge of the following models using mergekit:

• meta-llama/Llama-2-7b-chat-hf
• meta-llama/Llama-2-13b-hf

🧩 Configuration

slices:
  - sources:
      - model: meta-llama/Llama-2-7b-chat-hf
        layer_range: [0, 16]
      - model: meta-llama/Llama-2-13b-hf
        layer_range: [0, 16]
merge_method: slerp
base_model: meta-llama/Llama-2-7b-chat-hf
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