UnFimbulvetr-20B-V2

Waifu to catch your attention

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

GGUF Tests

Seems usable. But I'm having difficulty telling if the stacked layers were beneficial. While I think there's something added, I really can't tell.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• Sao10K/Fimbulvetr-11B-v2

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: Sao10K/Fimbulvetr-11B-v2
      layer_range: [0, 13]
  - sources:
    - model: Sao10K/Fimbulvetr-11B-v2
      layer_range: [8, 13]
  - sources:
    - model: Sao10K/Fimbulvetr-11B-v2
      layer_range: [12, 36]
  - sources:
    - model: Sao10K/Fimbulvetr-11B-v2
      layer_range: [12, 36]
  - sources:
    - model: Sao10K/Fimbulvetr-11B-v2
      layer_range: [20, 36]
  - sources:
    - model: Sao10K/Fimbulvetr-11B-v2
      layer_range: [36, 48]
merge_method: passthrough
dtype: bfloat16