Masterjp123/P1

merged

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using NousResearch/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

• NousResearch/Hermes-2-Pro-Llama-3-8B
• Weyaxi/Einstein-v6.1-Llama3-8B
• asiansoul/Versatile-Llama-3-8B-1m

Configuration

The following YAML configuration was used to produce this model:

base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
slices:
- sources:
  - layer_range: [0, 32]
    model: Weyaxi/Einstein-v6.1-Llama3-8B
    parameters:
      density: 0.1
      weight: 1.0
  - layer_range: [0, 32]
    model: asiansoul/Versatile-Llama-3-8B-1m
    parameters:
      density: 0.2
      weight: 0.35
  - layer_range: [0, 32]
    model: NousResearch/Hermes-2-Pro-Llama-3-8B
    parameters:
      density: 0.5
      weight: 0.23
  - layer_range: [0, 32]
    model: NousResearch/Meta-Llama-3-8B