Carasique-v0.1

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

Merge Details

Merge Method

This model was merged using the della_linear merge method using unsloth/Mistral-Nemo-Base-2407 as a base.

Models Merged

The following models were included in the merge:

• nlpguy/StableProse
• TheDrummer/Rocinante-12B-v1
• Sao10K/MN-12B-Lyra-v2a1
• nbeerbower/mistral-nemo-gutenberg-12B-v3
• unsloth/Mistral-Nemo-Instruct-2407

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/Mistral-Nemo-Instruct-2407
    parameters:
      weight: 0.1
      density: 0.4
  - model: nlpguy/StableProse
    parameters:
      weight: 0.12
      density: 0.5
  - model: Sao10K/MN-12B-Lyra-v2a1
    parameters:
      weight: 0.2
      density: 0.6
  - model: TheDrummer/Rocinante-12B-v1
    parameters:
      weight: 0.25
      density: 0.7
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v3
    parameters:
      weight: 0.33
      density: 0.8
merge_method: della_linear
base_model: unsloth/Mistral-Nemo-Base-2407
parameters:
  epsilon: 0.05
  lambda: 1
dtype: bfloat16