This one didn't come out right, I feel it's inferior to it's predecessor. But that is only from early testing.

merge

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

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using nbeerbower/Llama-3.1-Nemotron-lorablated-70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Steelskull/L3.3-MS-Nevoria-70b
    parameters:
      weight: 0.20
      density: 0.7
  - model: Nohobby/L3.3-Prikol-70B-v0.3
    parameters:
      weight: 0.20
      density: 0.7
  - model: Tarek07/Progenitor-V1.2-LLaMa-70B
    parameters:
      weight: 0.20
      density: 0.7
  - model: Tarek07/Progenitor-V1.1-LLaMa-70B
    parameters:
      weight: 0.20
      density: 0.7
  - model: sophosympatheia/Nova-Tempus-70B-v0.1
    parameters:
      weight: 0.20
      density: 0.7
merge_method: della_linear
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
parameters:
  epsilon: 0.2
  lambda: 1.1
dtype: bfloat16
tokenizer_source: base