mergekit-community/mergekit-dare_ties-woeufhp

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using nvidia/Llama-3.1-Nemotron-70B-Instruct-HF as a base.

Models Merged

The following models were included in the merge:

• unsloth/Llama-3.3-70B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/Llama-3.3-70B-Instruct
    parameters:
      density: 0.30
      weight: 0.50
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
    parameters:
      density: 0.50
      weight: 0.75
merge_method: dare_ties
base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
parameters:
  normalize: true
  int8_mask: true
dtype: float16