TareksLab/Progenitor-V2.3-LLaMa-70B

I am experimenting with some of the DELLA merge method parameters.

Progenitor-V2.3-70B

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 nbeerbower/Llama-3.1-Nemotron-lorablated-70B as a base.

Models Merged

The following models were included in the merge:

EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 Sao10K/L3.1-70B-Hanami-x1 Sao10K/70B-L3.3-Cirrus-x1 TheDrummer/Anubis-70B-v1 SicariusSicariiStuff/Negative_LLAMA_70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/L3.1-70B-Hanami-x1
    parameters:
      weight: 0.20
  - model: Sao10K/70B-L3.3-Cirrus-x1
    parameters:
      weight: 0.20
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.20
  - model: TheDrummer/Anubis-70B-v1
    parameters:
      weight: 0.20
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      weight: 0.20
merge_method: della
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
parameters:
  density: 0.7
  epsilon: 0.15
  lambda: 1.1
  rescale: 1
  window_size: 0.14
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union