baccules-3b-slerp / README.md
limin(gate)
Upload folder using huggingface_hub
a667e8d verified
|
raw
history blame contribute delete
No virus
931 Bytes
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - indischepartij/MiniCPM-3B-Hercules-v2.0
  - indischepartij/MiniCPM-3B-Bacchus

baccules-3b-slerp

baccules-3b-slerp is a merge of the following models using mergekit:

🧩 Configuration

slices:
  - sources:
      - model: indischepartij/MiniCPM-3B-Hercules-v2.0
        layer_range: [0, 40]
      - model: indischepartij/MiniCPM-3B-Bacchus
        layer_range: [0, 40]
merge_method: slerp
base_model: indischepartij/MiniCPM-3B-Hercules-v2.0
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