bunnycore/LLama-3.1-8b-Ultra-Max-Pro

merge

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 vicgalle/Configurable-Llama-3.1-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• AGI-0/Artificium-llama3.1-8B-001
• Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
• Dampfinchen/Llama-3.1-8B-Ultra-Instruct
• NousResearch/Hermes-3-Llama-3.1-8B
• bunnycore/LLama-3.1-Hyper-Stock

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Dampfinchen/Llama-3.1-8B-Ultra-Instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/LLama-3.1-Hyper-Stock
    parameters:
      density: 0.5
      weight: 0.5
  - model: AGI-0/Artificium-llama3.1-8B-001
    parameters:
      density: 0.5
      weight: 0.5
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    parameters:
      density: 0.5
      weight: 0.5
  - model: NousResearch/Hermes-3-Llama-3.1-8B
    parameters:
      density: 0.5
      weight: 0.5
  - model: vicgalle/Configurable-Llama-3.1-8B-Instruct
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: vicgalle/Configurable-Llama-3.1-8B-Instruct
parameters:
  normalize: false
  int8_mask: true
dtype: float16