|
--- |
|
license: gpl-3.0 |
|
language: |
|
- en |
|
- zh |
|
|
|
inference: false |
|
--- |
|
|
|
# Ziya-LLaMA-13B-v1 |
|
|
|
- Main Page:[Fengshenbang](https://fengshenbang-lm.com/) |
|
- Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM) |
|
|
|
（LLaMA权重的许可证限制，我们无法直接发布完整的模型权重，用户需要参考[使用说明](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1)进行合并) |
|
|
|
# 姜子牙系列模型 |
|
|
|
- [Ziya-LLaMA-13B-v1](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1) |
|
- [Ziya-LLaMA-7B-Reward](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-7B-Reward) |
|
- [Ziya-LLaMA-13B-Pretrain-v1](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1) |
|
- [Ziya-BLIP2-14B-Visual-v1](https://huggingface.co/IDEA-CCNL/Ziya-BLIP2-14B-Visual-v1) |
|
|
|
## 简介 Brief Introduction |
|
我们对Ziya-LLaMA-13B-v1模型进行继续优化，推出开源版本Ziya-LLaMA-13B-v1.1。通过调整微调数据的比例和采用更优的强化学习策略，本版本在问答准确性、数学能力以及安全性等方面得到了明显提升，详细能力分析如下图所示。 |
|
|
|
We have further optimized the Ziya-LLaMA-13B-v1 model and released the open-source version Ziya-LLaMA-13B-v1.1. By adjusting the proportion of fine-tuning data and adopting a better reinforcement learning strategy, this version has achieved significant improvements in question-answering accuracy, mathematical ability, and safety, as shown in the following figure in detail. |
|
|
|
<img src="https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1.1/resolve/main/pk.png" width=1000 height=600> |
|
|
|
## 软件依赖 |
|
``` |
|
pip install torch==1.12.1 tokenizers==0.13.3 git+https://github.com/huggingface/transformers |
|
``` |
