JY623's picture
Update README.md
b3d3709 verified
metadata
base_model:
  - hyeogi/SOLAR-10.7B-v1.5
  - yanolja/KoSOLAR-10.7B-v0.2
library_name: transformers
tags:
  - mergekit
  - merge
license: apache-2.0

slerp_test1

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: yanolja/KoSOLAR-10.7B-v0.2
      layer_range: [0, 48]
    - model: hyeogi/SOLAR-10.7B-v1.5
      layer_range: [0, 48] 

merge_method: slerp
base_model: yanolja/KoSOLAR-10.7B-v0.2
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: float16