metadata
language:
- en
- zh
pipeline_tag: text-generation
hongyin/chat-informer-120b-80k
I am pleased to introduce an English-Chinese conversation assistant designed to reduce the cost of inference. It is trained based on the goliath-120B, with a unique vocabulary and 120 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: 法国的首都
Assistant: French: Pairs
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}
}