Modelpublic

grimjim/BadApple-o1-Llama-3.1-8B

sourceHugging Facellama3.1updated 2y agoView on Hugging Face

1likes19downloads

Model Card

BadApple-o1-Llama-3.1-8B

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

Ask the model to generate poetry with offbeat formatting. You know you want to.

Built with Llama.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

—grimjim/HuatuoSkywork-o1-Llama-3.1-8B
—kalomaze/bad-apple-8b-v1

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: grimjim/HuatuoSkywork-o1-Llama-3.1-8B
  - model: kalomaze/bad-apple-8b-v1
merge_method: slerp
base_model: grimjim/HuatuoSkywork-o1-Llama-3.1-8B
parameters:
  t:
   - value: 0.9
dtype: bfloat16