llama3-1b-della-v1

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 meta-llama/Llama-3.2-1B as a base.

Models Merged

The following models were included in the merge:

• Alelcv27/llama3-1b-math-dpo
• Alelcv27/llama3-1b-code-dpo

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Llama-3.2-1B
dtype: float16
merge_method: della
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 16]
        model: Alelcv27/llama3-1b-math-dpo
        parameters:
          density: 0.8
          weight: 0.7
      - layer_range: [0, 16]
        model: Alelcv27/llama3-1b-code-dpo
        parameters:
          density: 0.8
          weight: 0.5
      - layer_range: [0, 16]
        model: meta-llama/Llama-3.2-1B
parameters:
  epsilon: 0.1
  lambda: 1.0
  normalize: 1.0