Llama-3.1-Bonsaikraft-8B-Instruct

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

This merge is a straightforward combination of German-English and Japanese-English Instruct models.

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:

• VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
• tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2

Configuration

The following YAML configuration was used to produce this model:

base_model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
dtype: bfloat16
merge_method: slerp
slices:
- sources:
  - model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
    layer_range: [0, 32]
  - model: tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2
    layer_range: [0, 32]
parameters:
  t:
    - value: 0.5