MiniButler-4B

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 Qwen3/4B/full/apollo_mini_writing/checkpoint-33758 as a base.

Models Merged

The following models were included in the merge:

• GreenerPastures/Basically-Human-4B
• hardlyworking/Sugma4B
• Hastagaras/Qibil-4B-v0.1-RP

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: hardlyworking/Sugma4B
    parameters:
      density: 0.7
      weight: 0.3
      epsilon: 0.25
  - model: GreenerPastures/Basically-Human-4B
    parameters:
      density: 0.7
      weight: 0.4
      epsilon: 0.25
  - model: Hastagaras/Qibil-4B-v0.1-RP
    parameters:
      density: 0.7
      weight: 0.3
      epsilon: 0.25
merge_method: della
base_model: Qwen3/4B/full/apollo_mini_writing/checkpoint-33758
dtype: bfloat16
parameters:
  normalize: false
  int8_mask: false
  lambda: 1.05