---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- noelabu/gemma-2b-instruct-ft-mental-health-conv
- GuelGaMesh01/gemma-2b-it-finetuned-mental-health-qa
---

# mental_chat_merge-gemma-2B

mental_chat_merge-gemma-2B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [noelabu/gemma-2b-instruct-ft-mental-health-conv](https://huggingface.co/noelabu/gemma-2b-instruct-ft-mental-health-conv)
* [GuelGaMesh01/gemma-2b-it-finetuned-mental-health-qa](https://huggingface.co/GuelGaMesh01/gemma-2b-it-finetuned-mental-health-qa)

## 🧩 Configuration

'''yaml
slices:
  - sources:
    - model: noelabu/gemma-2b-instruct-ft-mental-health-conv
      layer_range: [0, 18]
    - model: GuelGaMesh01/gemma-2b-it-finetuned-mental-health-qa
      layer_range: [0, 18]
merge_method: slerp
base_model: GuelGaMesh01/gemma-2b-it-finetuned-mental-health-qa
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
'''