mergekit-community/mergekit-task_arithmetic-haaopre

merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using DebateLabKIT/Llama-3.1-Argunaut-1-8B-SFT as a base.

Models Merged

The following models were included in the merge:

• allenai/Llama-3.1-Tulu-3-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: DebateLabKIT/Llama-3.1-Argunaut-1-8B-SFT
    parameters:
      weight: 1.0  # Base model (no scaling)
  - model: allenai/Llama-3.1-Tulu-3-8B
    parameters:
      weight: 0.5  # Task-specific model (scaled by 0.5)

merge_method: task_arithmetic  # Use task arithmetic for merging

base_model: DebateLabKIT/Llama-3.1-Argunaut-1-8B-SFT  # Explicitly define the base model