djuna/L3.1-Purosani

merge

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

Merge Details

Merge Method

This model was merged using the della_linear merge method using arcee-ai/Llama-3.1-SuperNova-Lite + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Models Merged

The following models were included in the merge:

• djuna/L3.1-Suze-Vume-calc
• hf-100/Llama-3-Spellbound-Instruct-8B-0.3
• djuna/L3.1-ForStHS + Blackroot/Llama-3-8B-Abomination-LORA
• THUDM/LongWriter-llama3.1-8b + ResplendentAI/Smarts_Llama3

Configuration

The following YAML configuration was used to produce this model:

merge_method: della_linear
dtype: bfloat16
parameters:
  epsilon: 0.1
  lambda: 1.0
  normalize: false
base_model: arcee-ai/Llama-3.1-SuperNova-Lite+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
models:
  - model: hf-100/Llama-3-Spellbound-Instruct-8B-0.3
    parameters:
      weight: 0.18
      density: 0.54
  - model: djuna/L3.1-ForStHS+Blackroot/Llama-3-8B-Abomination-LORA
    parameters:
      weight: 0.22
      density: 0.5
  - model: djuna/L3.1-Suze-Vume-calc
    parameters:
      weight: 0.13
      density: 0.49
  - model: THUDM/LongWriter-llama3.1-8b+ResplendentAI/Smarts_Llama3
    parameters:
      weight: 0.18
      density: 0.55