GPT-2: 6-Month Follow-Up

[lifelonglearner]

Linkpost for GPT-2 6 Month Follow-Up.

Some highlights:

• 700+ M parameter model is being released

• Several other groups have reproduced similar models

• In detecting synthesized text, “current ML-based methods only achieve low to mid–90s accuracy”

[Dr_Manhattan]

Also notable: NVIDIA trained a half-order-of-magnitude larger model https://​​nv-adlr.github.io/​​MegatronLM?utm_campaign=NLP%20News&utm_medium=email&utm_source=Revue%20newsletter