majuli-4

majuli-4

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 mistralai/Mistral-7B-Instruct-v0.2 as a base.

Models Merged

The following models were included in the merge:

• NousResearch/Hermes-2-Pro-Mistral-7B
• teknium/OpenHermes-2.5-Mistral-7B

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    parameters:
      weight: 0.2
      density: 0.7
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      weight: 0.4
      density: 0.7
  - model: NousResearch/Hermes-2-Pro-Mistral-7B
    parameters:
      weight: 0.4
      density: 0.7
parameters:
  int8_mask: true
dtype: bfloat16