Update README.md

README.md

@@ -12,3 +12,10 @@ language:
 #### 需要注意的是，TiLamb-7B为未经微调的base模型，无对话能力，需SFT进行藏文对话和藏文NLP下游任务（已验证过的有：藏文新闻分类、藏文实体关系分类、藏文机器阅读理解、藏文分词、藏文摘要、藏文问题回答、藏文问题生成）的适配。
 
 #### 说明：本项目基于由Meta发布的LLaMA2-7B模型进行开发，使用过程中请严格遵守LLaMA2-7B的开源许可协议。如果涉及使用第三方代码，请务必遵从相关的开源许可协议。模型生成的内容可能会因为计算方法、随机因素等影响其准确性，因此，本项目不对模型输出的准确性提供任何保证，也不会对任何因使用相关资源和输出结果产生的损失承担责任。如果将本项目的相关模型用于商业用途，开发者应遵守当地的法律法规，确保模型输出内容的合规性，本项目不对任何由此衍生的产品或服务承担责任。
+
+### TiLamb-7B (Tibetan Large Language Model Base) is the base model for the Tibetan large language model, utilizing 26.43GB of Tibetan textual corpus. It is incrementally pre-trained on the LLaMA2-7B model using the LoRA method. TiLamb-7B has expanded the LLaMA2 vocabulary by incorporating a Tibetan lexicon, increasing the original vocabulary size from 32,000 to 61,221. It also initializes the embedding and lm_head with mean expansion.
+
+#### It is important to note that TiLamb-7B, as an unrefined base model, lacks conversational capabilities. It requires Supervised Fine-Tuning (SFT) for adaptation to Tibetan conversational applications and other NLP downstream tasks in Tibetan (which have been verified to include: Tibetan news classification, Tibetan entity relation classification, Tibetan machine reading comprehension, Tibetan word segmentation, Tibetan summarization, Tibetan question answering, and Tibetan question generation).
+
+#### Disclaimer: This project is developed based on the LLaMA2-7B model released by Meta, and users must strictly adhere to the open-source license agreement of LLaMA2-7B during use. If third-party code is used, it is imperative to comply with the relevant open-source licenses. The accuracy of the content generated by the model may be affected by computational methods and random factors; therefore, this project does not guarantee the accuracy of the model's outputs and will not be responsible for any loss incurred from using the related resources and outputs. If this project's models are used for commercial purposes, developers must comply with local laws and regulations to ensure the compliance of the model outputs. The project will not be liable for any products or services derived from this use.
+