Novaciano/Corrupted_Dolphin-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 dphn/Dolphin3.0-Llama3.2-1B as a base.

Models Merged

The following models were included in the merge:

• marcuscedricridia/badllama3.2-1B
• CodeAtCMU/Llama-3.2-1B-GenerativePerturbations_full_sft_code_data_120K_imaginary
• syvai/emotion-reasoning-1b

Configuration

The following YAML configuration was used to produce this model:

models:
- model: marcuscedricridia/badllama3.2-1B
- model: CodeAtCMU/Llama-3.2-1B-GenerativePerturbations_full_sft_code_data_120K_imaginary
- model: syvai/emotion-reasoning-1b
merge_method: model_stock
base_model: dphn/Dolphin3.0-Llama3.2-1B
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0]