checkpoint-1470-merged

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:

/workspace/HUB_LLM/Llama-3.3-70B-Instruct
/workspace/HUB_LLM/010225_llama33_70b_instruct/checkpoint-1470

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: /workspace/HUB_LLM/Llama-3.3-70B-Instruct
        layer_range: [0, 80]
      - model: /workspace/HUB_LLM/010225_llama33_70b_instruct/checkpoint-1470
        layer_range: [0, 80]
        
merge_method: slerp
base_model: /workspace/HUB_LLM/Llama-3.3-70B-Instruct
parameters:
  t:
    - filter: self_attn
      value: [0, 0.3, 0.5, 0.7, 1]
    - filter: mlp
      value: [1, 0.7, 0.5, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16