slu-23 / README.md
jaspionjader's picture
Upload folder using huggingface_hub
9815044 verified
|
raw
history blame
1.18 kB
metadata
base_model:
  - jaspionjader/Kosmos-EVAA-immersive-sof-v44-8B
  - jaspionjader/slu-22
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:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: jaspionjader/Kosmos-EVAA-immersive-sof-v44-8B
    layer_range:
    - 0
    - 32
  - model: jaspionjader/slu-22
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: jaspionjader/Kosmos-EVAA-immersive-sof-v44-8B
parameters:
  t:
  - filter: self_attn
    value:
    - 0.23
    - 0.76
    - 0.79
    - 0.82
    - 0.37
  - filter: mlp
    value:
    - 0.37
    - 0.82
    - 0.79
    - 0.76
    - 0.23
  - value: 0.17
dtype: bfloat16