Dataset ideas:

• BoolQ
• IMDB sentiment classification text
• HateXplain
• MASSIVE

Interesting read: https://arxiv.org/abs/2305.07759

@misc{eldan2023tinystoriessmalllanguagemodels, title={TinyStories: How Small Can Language Models Be and Still Speak Coherent English?}, author={Ronen Eldan and Yuanzhi Li}, year={2023}, eprint={2305.07759}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2305.07759}, }

Current demo ideas:

• character generation
• token generation
• sentence reversal