Nohobby/YetAnotherMerge-v0.3

merge

This one turned out really good imo. Works fine with the basic min-p settings, but I recommend using this preset I made.

iMatrix GGUF Static GGUF

Merge Details

Merge Method

This model was merged using the della merge method using Undi95/Lumimaid-Magnum-12B as a base.

Models Merged

The following models were included in the merge:

• Sao10K/MN-12B-Lyra-v1
• Nohobby/YetAnotherMerge-v0.1

Configuration

The following YAML configuration was used to produce this model:

base_model: Undi95/Lumimaid-Magnum-12B
parameters:
  int8_mask: true
  rescale: true
  normalize: false
merge_method: della
dtype: bfloat16
models:
  - model: Sao10K/MN-12B-Lyra-v1
    parameters:
      density: [0.4, 0.5, 0.6, 0.4, 0.6, 0.5, 0.4]
      epsilon: [0.15, 0.15, 0.25, 0.15, 0.15]
      lambda: 0.85
      weight: [0.6, 0.5, 0.4, 0.6, 0.4, 0.5, 0.6]
  - model: Nohobby/YetAnotherMerge-v0.1
    parameters:
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
      epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
      lambda: 0.85
      weight: [0.55, 0.45, 0.55, 0.45, 0.55]