metadata

base_model:
  - meta-llama/Meta-Llama-3-8B-Instruct
  - ChaoticNeutrals/Domain-Fusion-L3-8B
  - ChaoticNeutrals/Hathor_RP-v.01-L3-8B
  - Sao10K/L3-8B-Stheno-v3.2
  - ChaoticNeutrals/Templar_v1_8B
  - ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

This is a test of the OVA merger technique on RP model merges.

Merge Method

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

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: meta-llama/Meta-Llama-3-8B-Instruct
  - model: ChaoticNeutrals/Templar_v1_8B
    parameters:
      weight: [0.33, 0.11, -0.11, 0, 0]
  - model: ChaoticNeutrals/Hathor_RP-v.01-L3-8B
    parameters:
      weight: [0.11, 0.33, 0.11, -0.11, 0]
  - model: Sao10K/L3-8B-Stheno-v3.2
    parameters:
      weight: [-0.11, 0.11, 0.33, 0.11, -0.11]
  - model: ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B
    parameters:
      weight: [0, -0.11, 0.11, 0.33, 0.11]
  - model: ChaoticNeutrals/Domain-Fusion-L3-8B
    parameters:
      weight: [0, 0, -0.11, 0.11, 0.33]
merge_method: task_arithmetic
base_model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
  normalize: false
dtype: bfloat16