Triangle104/Metabolic-Llama_V1.0

Model details:

A test... of sorts? It seems to like Alpaca Template format, and while it does provide uncensoring, it's not heavy on it.

merge

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

Merge Method

This model was merged using the TIES merge method using unsloth/Meta-Llama-3.1-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
• huihui-ai/Llama-3.1-Tulu-3-8B-abliterated

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/Meta-Llama-3.1-8B-Instruct
    #no parameters necessary for base model
  - model: huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
    parameters:
      density: 0.5
      weight: 0.5
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
parameters:
  normalize: true
  int8_mask: true
dtype: float16