yamatazen/Ayla-Light-12B

UGI leaderboard results

merge

This is a merge of pre-trained language models 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:

• nbeerbower/mistral-nemo-gutenberg-12B-v4 + nbeerbower/Mistral-Nemo-12B-abliterated-LORA
• Elizezen/Himeyuri-v0.1-12B

Configuration

The following YAML configuration was used to produce this model:

base_model: nbeerbower/mistral-nemo-gutenberg-12B-v4+nbeerbower/Mistral-Nemo-12B-abliterated-LORA
models:
  - model: Elizezen/Himeyuri-v0.1-12B
merge_method: slerp
dtype: bfloat16
parameters:
  normalize: true
  t: [0.25,0.3,0.5,0.3,0.25]