README.md

metadata

base_model:
  - ajibawa-2023/Code-Llama-3-8B
  - Jebadiah/Tess-gradient-ruby-p2
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 linear DARE merge method using Jebadiah/Tess-gradient-ruby-p2 as a base.

Models Merged

The following models were included in the merge:

• ajibawa-2023/Code-Llama-3-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Jebadiah/Tess-gradient-ruby-p2
    # No parameters necessary for base model
  - model: ajibawa-2023/Code-Llama-3-8B
    parameters:
      density: 0.5
      weight: 0.5
merge_method: dare_linear
base_model: Jebadiah/Tess-gradient-ruby-p2
parameters:
  int8_mask: true
dtype: bfloat16