---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- FreedomIntelligence/HuatuoGPT2-7B
- TheBloke/Llama-2-7B-Chat-GPTQ
---

# migatwogptllama

migatwogptllama is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [FreedomIntelligence/HuatuoGPT2-7B](https://huggingface.co/FreedomIntelligence/HuatuoGPT2-7B)
* [TheBloke/Llama-2-7B-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GPTQ)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: FreedomIntelligence/HuatuoGPT2-7B
        layer_range: [0, 32]
      - model: TheBloke/Llama-2-7B-Chat-GPTQ
        layer_range: [0, 32]
merge_method: slerp
base_model: TheBloke/Llama-2-7B-Chat-GPTQ
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

```