The base model is meta's Llama-2-7b-chat-hf. It was finetuned using SFT and the openassistant/oasst1 dataset and the model prompt is similar to the original Guanaco model. 
This repo contains the merged fp16 model.

**Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.**
---
- license: 
  - llama2 <br>
- datasets:
  - openassistant/oasst1 <br>
- language:
  - en <br>
- reference: https://gist.github.com/younesbelkada/9f7f75c94bdc1981c8ca5cc937d4a4da
---
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheTravellingEngineer__llama2-7b-chat-hf-v4)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 43.47   |
| ARC (25-shot)         | 53.41          |
| HellaSwag (10-shot)   | 78.56    |
| MMLU (5-shot)         | 46.43         |
| TruthfulQA (0-shot)   | 38.71   |
| Winogrande (5-shot)   | 74.03   |
| GSM8K (5-shot)        | 7.51        |
| DROP (3-shot)         | 5.61         |