jeiku/DareNutz

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 unsloth/mistral-7b-instruct-v0.3 as a base.

Models Merged

The following models were included in the merge:

• unsloth/mistral-7b-instruct-v0.3 + jeiku/Theory_of_Mind_Mistral
• unsloth/mistral-7b-instruct-v0.3 + jeiku/Synthetic_Soul_1k_Mistral_128
• unsloth/mistral-7b-instruct-v0.3 + jeiku/Luna_LoRA_Mistral

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/mistral-7b-instruct-v0.3+jeiku/Theory_of_Mind_Mistral
    parameters:
      density: 1
      weight: 1
  - model: unsloth/mistral-7b-instruct-v0.3+jeiku/Luna_LoRA_Mistral
    parameters:
      density: 1
      weight: 1
  - model: unsloth/mistral-7b-instruct-v0.3+jeiku/Synthetic_Soul_1k_Mistral_128
    parameters:
      density: 1
      weight: 1
merge_method: dare_ties
base_model: unsloth/mistral-7b-instruct-v0.3
parameters:
  normalize: true
dtype: bfloat16