QuantFactory/Llama-3.1-8B-OmniMatrix-v2-GGUF

This is quantized version of bunnycore/Llama-3.1-8B-OmniMatrix-v2 created using llama.cpp

Original Model Card

merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using bunnycore/Llama-3.1-8B-OmniMatrix + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Models Merged

The following models were included in the merge:

• refuelai/Llama-3-Refueled
• bunnycore/Llama-3.1-8B-OmniMatrix
• grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
• bunnycore/LLama-3.1-8B-HyperNova-abliteration

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
    parameters:
      weight: 1.0
  - model: bunnycore/LLama-3.1-8B-HyperNova-abliteration
    parameters:
      weight: 1.0
  - model: refuelai/Llama-3-Refueled
    parameters:
      weight: 1.0
  - model: bunnycore/Llama-3.1-8B-OmniMatrix
    parameters:
      weight: 1.0

merge_method: task_arithmetic
base_model: bunnycore/Llama-3.1-8B-OmniMatrix+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
    normalize: false
dtype: float16