bunnycore/Llama-3.2-3B-Deep-Test

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using bunnycore/Llama-3.2-3B-RP-DeepThink as a base.

Models Merged

The following models were included in the merge:

• prithivMLmods/Llama-Deepsync-3B
• bunnycore/Llama-3.2-3B-All-Mix
• bunnycore/Smol-Llama-3.2-3B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Llama-3.2-3B-RP-DeepThink
    parameters:
      weight: 0.5
  - model: bunnycore/Smol-Llama-3.2-3B
    parameters:
      weight: 0.5
  - model: prithivMLmods/Llama-Deepsync-3B
    parameters:
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-All-Mix
    parameters:
      weight: 0.5
base_model: bunnycore/Llama-3.2-3B-RP-DeepThink
merge_method: dare_ties