Mermaid-Coder-Llama-3-8B

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• dbands/llama-3-8b-instruct_code_instructions_122k_alpaca_style_16bit
• artificialguybr/llama3-8b-redmond-code290k

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: dbands/llama-3-8b-instruct_code_instructions_122k_alpaca_style_16bit
        layer_range: [0, 32]
      - model: artificialguybr/llama3-8b-redmond-code290k
        layer_range: [0, 32]
      # - model: TroyDoesAI/Mermaid-Llama-3-8B
      #   layer_range: [0, 32]

      # - model: TroyDoesAI/Mermaid-Llama-3-8B
      #   layer_range: [0, 32]
      # - model: TroyDoesAI/Mermaid-Llama-8B-Laser-High-SNR
      #   layer_range: [0, 32]
      
merge_method: slerp
base_model: dbands/llama-3-8b-instruct_code_instructions_122k_alpaca_style_16bit
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 # fallback for rest of tensors
dtype: float16