---
license: other
language:
- en
---
## Model Details
This is an unofficial implementation of "[AlpaGasus: Training a better Alpaca with Fewer Data.](https://github.com/Lichang-Chen/AlpaGasus)" with [LLaMA2](https://huggingface.co/meta-llama/Llama-2-13b-hf) & QLoRA! Training code is available at our [repo](https://github.com/gauss5930/AlpaGasus2-QLoRA). 

- **Developed by:** [Yunsang Yoo](https://huggingface.co/ryan0712) and [Hyunwoo Ko](https://huggingface.co/Cartinoe5930)
- **Model type:** Auto-regressive model
- **Language(s):** English
- **Base Model:** [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf)
- **License**: Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/))



### Benchmark Metrics
| Metric                | Value |
|-----------------------|-------|
| MMLU                  | 55.27 |
| ARC                   | 61.09 |
| HellaSwag             | 82.46 |
| TruthfulQA            | 38.53 |
| Avg.                  | 59.34 |

### Training Dataset

"StudentLLM/Alpagasus-2-13b-QLoRA-merged" used [gpt4life](https://github.com/gpt4life/alpagasus)'s gpt-3.5-turbo filtered dataset, 'alpaca_t45.json'.
Configuration of the dataset is as follows:

### Prompt Template
```
### Instruction:

<prompt> (without the <>)

### Response:
```