mergekit-community/mergekit-linear-mnfmxyq

merge

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

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

• allenai/Llama-3.1-Tulu-3.1-8B
• huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
• djuna-test-lab/mergekit-linear-jyaduup
• djuna-test-lab/mergekit-linear-mwacdwp

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
    parameters:
      weight: 0.2
  - model: allenai/Llama-3.1-Tulu-3.1-8B
    parameters:
      weight: 0.3
  - model: djuna-test-lab/mergekit-linear-jyaduup
    parameters:
      weight: 0.3
  - model: djuna-test-lab/mergekit-linear-mwacdwp
    parameters:
      weight: 0.2
merge_method: linear
dtype: bfloat16
tokenizer_source: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
parameters:
  normalize: false