QuantFactory/L3-Luna-8B-GGUF

This is quantized version of Casual-Autopsy/L3-Luna-8B 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 TIES merge method using Sao10K/L3-8B-Lunaris-v1 as a base.

Models Merged

The following models were included in the merge:

• FPHam/L3-8B-Everything-COT
• ChaoticNeutrals/Domain-Fusion-L3-8B
• Ayush-1722/Meta-Llama-3-8B-Instruct-Summarize-v0.2-24K-LoRANET-Merged
• Sao10K/L3-8B-Niitama-v1
• nothingiisreal/L3-8B-Celeste-V1.2
• Orenguteng/Llama-3-8B-Lexi-Uncensored
• OEvortex/Emotional-llama-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/L3-8B-Lunaris-v1
  - model: FPHam/L3-8B-Everything-COT
    parameters:
        density: 0.5
        weight: 0.1
  - model: Ayush-1722/Meta-Llama-3-8B-Instruct-Summarize-v0.2-24K-LoRANET-Merged
    parameters:
        density: 0.5
        weight: 0.1
  - model: OEvortex/Emotional-llama-8B
    parameters:
        density: 0.5
        weight: 0.1
  - model: ChaoticNeutrals/Domain-Fusion-L3-8B
    parameters:
        density: 0.75
        weight: 0.05
  - model: nothingiisreal/L3-8B-Celeste-V1.2
    parameters:
        density: 0.75
        weight: 0.05
  - model: Orenguteng/Llama-3-8B-Lexi-Uncensored
    parameters:
        density: 0.75
        weight: 0.05
  - model: Sao10K/L3-8B-Niitama-v1
    parameters:
        density: 0.75
        weight: 0.05
base_model: Sao10K/L3-8B-Lunaris-v1
merge_method: ties
parameters:
  normalize: true
dtype: bfloat16