README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy
- TVRRaviteja/Llama-2-7b-chat-Counsel-finetuned
---

# mental_chat_merge2-llama-2-7B

mental_chat_merge2-llama-2-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy](https://huggingface.co/vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy)
* [TVRRaviteja/Llama-2-7b-chat-Counsel-finetuned](https://huggingface.co/TVRRaviteja/Llama-2-7b-chat-Counsel-finetuned)

## 🧩 Configuration

'''yaml
slices:
  - sources:
    - model: vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy
      layer_range: [0, 32]
    - model: TVRRaviteja/Llama-2-7b-chat-Counsel-finetuned
      layer_range: [0, 32]
merge_method: slerp
base_model: vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy
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
'''