update readme

README.md

@@ -47,7 +47,7 @@ pipeline_tag: text-generation
 
 # 1. Model Introduction
 
-- **Orion-14B-Chat-RAG:**  A chat-model fine-tuned on a custom retrieval augmented generation dataset, achieving superior performance in retrieval augmented generation tasks.
+- **Orion-14B-Chat-RAG:**  A chat-model fine-tuned on a custom retrieval augmented generation dataset, achieving superior performance in retrieval augmented generation tasks. For usage, please refer to [demo](https://github.com/OrionStarAI/Orion/tree/master/gradio_demo/doc_qa_task).
 
 - Orion-14B series models are open-source multilingual large language models trained from scratch by OrionStarAI.  The base model is trained on 2.5T multilingual corpus, including Chinese, English, Japanese, Korean, etc, and it exhibits superior performance in these languages.  For details, please refer to [tech report](https://github.com/OrionStarAI/Orion/blob/master/doc/Orion14B_v3.pdf).
 

README_cn.md

@@ -47,7 +47,7 @@ pipeline_tag: text-generation
 
 # 1. 模型介绍
 
-- **Orion-14B-Chat-RAG:**  在一个定制的检索增强生成数据集上进行微调的聊天模型，在检索增强生成任务中取得了卓越的性能。
+- **Orion-14B-Chat-RAG:**  在一个定制的检索增强生成数据集上进行微调的聊天模型，在检索增强生成任务中取得了卓越的性能。使用方法请参考[demo](https://github.com/OrionStarAI/Orion/tree/master/gradio_demo/doc_qa_task)。
 
 - Orion-14B-Base是一个具有140亿参数的多语种大模型，该模型在一个包含2.5万亿token的多样化数据集上进行了训练，涵盖了中文、英语、日语、韩语等多种语言。在多语言环境下的一系列任务中展现出卓越的性能。在主流的公开基准评测中，Orion-14B系列模型表现优异，多项指标显著超越同等参数基本的其他模型。具体技术细节请参考[技术报告](https://github.com/OrionStarAI/Orion/blob/master/doc/Orion14B_v3.pdf)。