Goutham-Vignesh's picture
Update README.md
ed7626d verified
|
raw
history blame
956 Bytes
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - nvidia/OpenMath-Mistral-7B-v0.1-hf
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.1

OpenMath-Mistral-7B-Merge-14-v0.1

OpenMath-Mistral-7B-Merge-14-v0.1 1 is a merge of the following models using mergekit:

🧩 Configuration

```yaml slices:

  • sources:
    • model: nvidia/OpenMath-Mistral-7B-v0.1-hf layer_range: [0, 32]
    • model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1 layer_range: [0, 32]

merge_method: slerp base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1 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 ```