EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0)

This is a merge of pre-trained language models created using mergekit. The purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

• Weyaxi/Einstein-v6.1-Llama3-8B
• jondurbin/bagel-8b-v1.0

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: meta-llama/Meta-Llama-3-8B
  - model: jondurbin/bagel-8b-v1.0
  - model: Weyaxi/Einstein-v6.1-Llama3-8B
merge_method: model_stock
base_model: meta-llama/Meta-Llama-3-8B
dtype: bfloat16