(GPT-2) Language Models are Unsupervised Multitask Learners | Paper Explained
1.8 هزار بار بازدید -
2 سال پیش
-
Here’s another video from my
Here’s another video from my GPT series where I analyze the GPT-2(Language Models are Unsupervised Multitasks Learners) paper. I took a closer look at data gathering process, results and safety concerns that prevented the initial public release of the model.
Paper:
https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Links:
https://huggingface.co/datasets
https://openai.com/blog/better-language-models/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Connect with me on:
Linkedin - https://www.linkedin.com/in/maciej-balawejder-rt8015/
GitHub - https://github.com/maciejbalawejder
Medium - https://medium.com/@maciejbalawejder
Buy Me a Coffee - [https://www.buymeacoffee.com/mbalawejder](https://www.buymeacoffee.com/mbalawejder)
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Timestamps:
https://www.seevid.ir/fa/w/9kT0XLPyHBg Introduction
https://www.seevid.ir/fa/w/9kT0XLPyHBg GPT-1 Recap
https://www.seevid.ir/fa/w/9kT0XLPyHBg Abstract
https://www.seevid.ir/fa/w/9kT0XLPyHBg Dataset
https://www.seevid.ir/fa/w/9kT0XLPyHBg Byte Pair Encoding
https://www.seevid.ir/fa/w/9kT0XLPyHBg Architecture
https://www.seevid.ir/fa/w/9kT0XLPyHBg Results
https://www.seevid.ir/fa/w/9kT0XLPyHBg Lambada
https://www.seevid.ir/fa/w/9kT0XLPyHBg CBT
https://www.seevid.ir/fa/w/9kT0XLPyHBg Winograd Schema Challenge
https://www.seevid.ir/fa/w/9kT0XLPyHBg CoQA
https://www.seevid.ir/fa/w/9kT0XLPyHBg Summarization
https://www.seevid.ir/fa/w/9kT0XLPyHBg Translation
https://www.seevid.ir/fa/w/9kT0XLPyHBg Question Answering
https://www.seevid.ir/fa/w/9kT0XLPyHBg Conclusions
https://www.seevid.ir/fa/w/9kT0XLPyHBg Safety Concerns
2 سال پیش
در تاریخ 1401/05/30 منتشر شده
است.
1,835
بـار بازدید شده