README.md

metadata

license: unlicense
tags:
  - merge
  - mergekit
  - lazymergekit
  - AI-B/UTENA-7B-UNA-V2
  - AI-B/UTENA-7B-NSFW-V2

UTENA-7B-V3

UTENA-7B-V3 is a merge of the following models using mergekit:

• AI-B/UTENA-7B-UNA-V2
• AI-B/UTENA-7B-NSFW-V2

🧩 Configuration

slices:
  - sources:
      - model: AI-B/UTENA-7B-UNA-V2
        layer_range: [0, 32]
      - model: AI-B/UTENA-7B-NSFW-V2
        layer_range: [0, 32]
merge_method: slerp
base_model: AI-B/UTENA-7B-UNA-V2
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16