mergekit-community/L3.1-Athena-m-8B

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using meta-llama/Llama-3.1-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• mergekit-community/L3.1-Athena-l4-8B
• DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
• mergekit-community/L3.1-Athena-l3-8B
• mergekit-community/L3.1-Athena-l2-8B
• DavidAU/L3.1-RP-Hero-BigTalker-8B
• DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B
• Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
• meta-llama/Llama-3.1-8B
• deepseek-ai/DeepSeek-R1-Distill-Llama-8B
• mergekit-community/L3.1-Athena-d-8B

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: meta-llama/Llama-3.1-8B-Instruct
models:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
    parameters:
      weight: 1.4
  - model: DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B
    parameters:
      weight: 1.4
  - model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
    parameters:
      weight: 1.2
  - model: DavidAU/L3.1-RP-Hero-BigTalker-8B
    parameters:
      weight: 1.2
  - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
    parameters:
      weight: 1.4
  - model: mergekit-community/L3.1-Athena-d-8B
    parameters:
      weight: 0.7
  - model: mergekit-community/L3.1-Athena-l2-8B
  - model: mergekit-community/L3.1-Athena-l3-8B
  - model: mergekit-community/L3.1-Athena-l4-8B
  - model: meta-llama/Llama-3.1-8B