Merge-DPO-v1ori / README.md
NischayDnk's picture
Upload folder using huggingface_hub
86dec6a verified
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - NischayDnk/Mistralnemo-dpo-v1-rp
  - mistralai/Mistral-Nemo-Instruct-2407

Merge-DPO-v1ori

Merge-DPO-v1ori is a merge of the following models using mergekit:

🧩 Configuration

```yaml slices:

  • sources:
    • model: NischayDnk/Mistralnemo-dpo-v1-rp layer_range: [0, 40]
    • model: mistralai/Mistral-Nemo-Instruct-2407 layer_range: [0, 40]

merge_method: slerp base_model: mistralai/Mistral-Nemo-Instruct-2407 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 ```