TareksLab/Protobase-DT1-LLaMa-70B

merge

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

Merge Details

Merge Method

This model was merged using the DELLA merge method using huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• Sao10K/L3.3-70B-Euryale-v2.3
• mlabonne/Hermes-3-Llama-3.1-70B-lorablated
• SicariusSicariiStuff/Negative_LLAMA_70B
• NaniDAO/Llama-3.3-70B-Instruct-ablated
• nbeerbower/Llama-3.1-Nemotron-lorablated-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
    parameters:
      weight: 0.20
      density: 0.5
  - model: Sao10K/L3.3-70B-Euryale-v2.3
    parameters:
      weight: 0.20
      density: 0.5
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.20
      density: 0.5
  - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
    parameters:
      weight: 0.20
      density: 0.5
  - model: NaniDAO/Llama-3.3-70B-Instruct-ablated
    parameters:
      weight: 0.20
      density: 0.5
merge_method: della
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
parameters:
  epsilon: 0.1
  lambda: 1.0
dtype: bfloat16
tokenizer:
 source: SicariusSicariiStuff/Negative_LLAMA_70B