README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- yam-peleg/Experiment26-7B
- EmbeddedLLM/Mistral-7B-Merge-14-v0.1
---

# 

Experiment26-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
* [EmbeddedLLM/Mistral-7B-Merge-14-v0.1](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1)

## 🧩 Configuration

```yaml
slices:
 - sources:
 - model: yam-peleg/Experiment26-7B
 layer_range: [0, 32]
 - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
 layer_range: [0, 32]
merge_method: slerp
base_model: yam-peleg/Experiment26-7B
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
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)


| Metric |Value|
|---------------------------------|----:|
|Avg. |74.96|
|AI2 Reasoning Challenge (25-Shot)|71.84|
|HellaSwag (10-Shot) |88.09|
|MMLU (5-Shot) |65.07|
|TruthfulQA (0-shot) |72.16|
|Winogrande (5-shot) |82.32|
|GSM8k (5-shot) |70.28|
```