magicadllama

magicadllama is a merge of the following models using mergekit:

• ise-uiuc/Magicoder-S-CL-7B
• NousResearch/Llama-2-7b-chat-hf

🧩 Configuration

slices:
  - sources:
    - model: ise-uiuc/Magicoder-S-CL-7B
      layer_range: [0, 32]
  - sources:
    - model: NousResearch/Llama-2-7b-chat-hf
      layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16