README.md

metadata

base_model:
  - ehristoforu/llama-3-12b-instruct
  - jsfs11/Llama-3-RPMerge-8B-SLERP
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• ehristoforu/llama-3-12b-instruct
• jsfs11/Llama-3-RPMerge-8B-SLERP
• Casual-Autopsy/L3-Deluxe-Scrambled-Eggs-On-Toast-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: ehristoforu/llama-3-12b-instruct
      layer_range: [0, 49]
  - sources:
    - model: jsfs11/Llama-3-RPMerge-8B-SLERP
      layer_range: [8, 32]
  - sources:
    - model: Casual-Autopsy/L3-Deluxe-Scrambled-Eggs-On-Toast-8B
      layer_range: [0, 32]
merge_method: passthrough
dtype: bfloat16