Edit model card

hongyin/chat-informer-70b-80k

I am pleased to introduce an English-Chinese conversation assistant designed to reduce the cost of inference. The original vocabulary lacked good support for Chinese, so the vocabulary was customized and expanded. It is trained based on the Llama2-chat-70B, with a unique vocabulary and 70 billion parameters.

Due to time constraints, I only performed a small amount of instruction fine-tuning, which resulted in shortcomings in the model's QA capabilities. I hope you can continue to fine-tune your instructions.

Losing fat is the only way to solve all problems.

Human: Say "I love you" differently in Chinese. 
Assistant:  "I love you" 是一个常见的句子,它表达了对某人的感情的强烈感受。这个句子的语法结构是主语“I”和谓语“ love”,其中“I”是主语,“ love”是谓语,表示主语对谓语的感情的强烈感受。

Bibtex entry and citation info

Please cite if you find it helpful.

@misc{zhu2023metaaid,
      title={MetaAID 2.5: A Secure Framework for Developing Metaverse Applications via Large Language Models}, 
      author={Hongyin Zhu},
      year={2023},
      eprint={2312.14480},
      archivePrefix={arXiv},
      primaryClass={cs.CR}
}

license: other

Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.