|
--- |
|
language: |
|
- en |
|
tags: |
|
- llama-2 |
|
- instruct |
|
- instruction |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# GenAI-llama-2-13b |
|
|
|
### Model Details |
|
- Developed by: [42MARU](https://www.42maru.ai/en/) |
|
- Backbone Model: [LLaMA-2](https://github.com/facebookresearch/llama/tree/main) |
|
- Library: [transformers](https://github.com/huggingface/transformers) |
|
|
|
### Used Datasets |
|
- Orca-style dataset |
|
- Platypus |
|
|
|
### Prompt Template |
|
``` |
|
### User: |
|
{User} |
|
|
|
### Assistant: |
|
{Assistant} |
|
``` |
|
|
|
### Intruduce 42MARU |
|
- At 42Maru we study QA (Question Answering) and are developing advanced search paradigms that help users spend less time searching by understanding natural language and intention thanks to AI and Deep Learning. |
|
- [About Us](https://www.42maru.ai/en/about-us/) |
|
- [Contact Us](https://www.42maru.ai/en/contact/) |
|
|
|
### Contribute |
|
- [l-yohai](https://github.com/l-yohai) |
|
|
|
|
|
### License |
|
[LICENSE.txt](meta-license/LICENSE.txt) |
|
|
|
### USE_POLICY |
|
[USE_POLICY.md](meta-license/USE_POLICY.md) |
|
|
|
### Responsible Use Guide |
|
[Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf) |
|
# [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_42MARU__sitebunny-13b) |
|
|
|
| Metric | Value | |
|
|-----------------------|---------------------------| |
|
| Avg. | 56.03 | |
|
| ARC (25-shot) | 63.14 | |
|
| HellaSwag (10-shot) | 83.64 | |
|
| MMLU (5-shot) | 59.91 | |
|
| TruthfulQA (0-shot) | 56.21 | |
|
| Winogrande (5-shot) | 76.72 | |
|
| GSM8K (5-shot) | 9.4 | |
|
| DROP (3-shot) | 43.23 | |
|
|
