README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- Eric111/Mistral-7B-Instruct-v0.2_openchat-3.5-0106
- eren23/dpo-binarized-NeuralTrix-7B
---

# MistInst-v0.2_ochat-3.5-0106_dpo-binarized-NeuralTrix-7B

MistInst-v0.2_ochat-3.5-0106_dpo-binarized-NeuralTrix-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [Eric111/Mistral-7B-Instruct-v0.2_openchat-3.5-0106](https://huggingface.co/Eric111/Mistral-7B-Instruct-v0.2_openchat-3.5-0106)
* [eren23/dpo-binarized-NeuralTrix-7B](https://huggingface.co/eren23/dpo-binarized-NeuralTrix-7B)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: Eric111/Mistral-7B-Instruct-v0.2_openchat-3.5-0106
        layer_range: [0, 32]
      - model: eren23/dpo-binarized-NeuralTrix-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: Eric111/Mistral-7B-Instruct-v0.2_openchat-3.5-0106
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

```