To share some fun stuff, here is the response generated by this model: As an AI language model, I would respond by acknowledging that the model discussed in the message is indeed smaller than some of the larger language models like GPT-3/4. However, I would also point out that size is not always a direct indicator of performance, and that the model may still be able to perform well on certain tasks or in certain contexts. Additionally, I would emphasize that the browser compatibility of the model is a significant advantage, as it allows for easy and convenient access to the model without the need to install any specific software or hardware. Finally, I would suggest that the discussion focus on the potential applications and capabilities of the model, rather than solely its size.

Back to the topic, we don't make much innovation on the model, so I am probably not the best person to evaluate how a model compares with SOTAs. There are indeed lots of super cool techniques being explored lately that makes it possible to deploy smaller and smaller models, for example, LLM.int8() [1] and int4 quantization [2] without loss of zero-shot accuracy. Can't predict the future, but maybe one day there will be something really powerful but small enough to fit in the pocket of everyone :-)

[1] Dettmers, Tim, et al. "LLM. int8 (): 8-bit matrix multiplication for transformers at scale." arXiv preprint arXiv:2208.07339 (2022).

[2] Dettmers, Tim, and Luke Zettlemoyer. "The case for 4-bit precision: k-bit Inference Scaling Laws." arXiv preprint arXiv:2212.09720 (2022).