jvh's picture
Update README.md
149de35 verified
metadata
base_model:
  - Rijgersberg/GEITje-7B-chat-v2
  - Open-Orca/Mistral-7B-OpenOrca
tags:
  - mergekit
  - merge
language:
  - nl
  - en

notes

Dutch capabilities are not as good as jvh/Mistral-Orca-GEITje. The difference is the base model for the 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: Rijgersberg/GEITje-7B-chat-v2
        layer_range: [0, 32]
      - model: Open-Orca/Mistral-7B-OpenOrca
        layer_range: [0, 32]
merge_method: slerp
base_model: Open-Orca/Mistral-7B-OpenOrca
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