Miscela-7b-slerp

Miscela-7b-slerp

This is a merge of two LLMs based on the Mistral architecture and pre-trained on the italian language! It has been 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:

• mii-community/zefiro-7b-sft-ITA
• DeepMount00/Mistral-Ita-7b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: mii-community/zefiro-7b-sft-ITA
        layer_range: [0, 32]
      - model: DeepMount00/Mistral-Ita-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: DeepMount00/Mistral-Ita-7b
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