base_model:

• mlabonne/gemma-3-4b-it-abliterated
• mshojaei77/gemma-3-4b-persian-v0
  library_name: transformers
  tags:
• mergekit
• merge

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• mlabonne/gemma-3-4b-it-abliterated
• mshojaei77/gemma-3-4b-persian-v0

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mlabonne/gemma-3-4b-it-abliterated
  - model: mshojaei77/gemma-3-4b-persian-v0
base_model: mlabonne/gemma-3-4b-it-abliterated
merge_method: slerp
dtype: bfloat16  # Better stability for precision-sensitive merges
parameters:
  density: 0.5
  weight: 
    - filter: "self_attn"
      value: [0.75, 0.4, 0.25, 0.4, 0.75]  # U-shaped attention weighting
    - filter: "mlp"
      value: [0.25, 0.6, 0.9, 0.6, 0.25]  # Λ-shaped MLP weighting
  t: [0.15, 0.35, 0.65, 0.35, 0.15]  # Optimized linguistic injection

generation_config = {
    "temperature": 1.1,
    "top_k": 50,
    "top_p": 0.9,
    "repetition_penalty": 1.15,
    "do_sample": True
}