Novaciano/Djinn-3.2-1B

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using qingy2024/Benchmaxx-Llama-3.2-1B-Instruct as a base.

Models Merged

The following models were included in the merge:

• unsloth/Llama-3.2-1B-Instruct
• diabolic6045/open-llama-3.2-1B-Instruct
• Xiaojian9992024/Llama3.2-1B-THREADRIPPER-v0.2
• SkyOrbis/SKY-Ko-Llama3.2-1B-lora-epoch5

Configuration

The following YAML configuration was used to produce this model:

models:
- model: SkyOrbis/SKY-Ko-Llama3.2-1B-lora-epoch5
- model: unsloth/Llama-3.2-1B-Instruct
- model: Xiaojian9992024/Llama3.2-1B-THREADRIPPER-v0.2
- model: diabolic6045/open-llama-3.2-1B-Instruct
base_model: qingy2024/Benchmaxx-Llama-3.2-1B-Instruct
merge_method: model_stock
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0]