Triangle104/Mistral-Humane-Gutenberg-10B

merge

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

Merge Details

Mistral-Nemo-Gutenberg with some humanity blended in.

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• nbeerbower/mistral-nemo-gutenberg3-12B
• HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: nbeerbower/mistral-nemo-gutenberg3-12B
        layer_range: [0, 32]
      - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
        layer_range: [0, 32]
merge_method: slerp
base_model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
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