Modelpublic

Nexesenex/Llama_3.1_8b_Smarteaz_0.21_SN

sourceHugging Faceupdated 2y agoView on Hugging Face

1likes11downloads

Model Card

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 grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B as a base.

Models Merged

The following models were included in the merge:

—huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
—huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: model_stock
models:
  - model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
    parameters:
      weight: 1.0
base_model: grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
dtype: bfloat16
normalize: true
chat_template: auto
tokenizer:
  source: union