flâneur

gpt-2/model_card.md at master · openai/gpt-2 · GitHub

github.com · 691 words · saved by 1 readers

Inspired by Model Cards for Model Reporting (Mitchell et al.), we’re providing some accompanying information about the GPT-2 family of models we're releasing. This model was developed by researchers at OpenAI to help us understand how the capabilities of language model capabilities scale as a function of the size of the models (by parameter count) combined with very large internet-scale datasets (WebText). February 2019, trained on data that cuts off at the end of 2017. Language model 1.5 billion parameters: the fourth and largest GPT-2 version. We have also released 124 million, 355 million, and 774 million parameter models. Blog post and paper Please use this Google Form The primary intended users of these models are AI researchers and practitioners. We primarily imagine these language models will be used by researchers to better understand the behaviors, capabilities, biases, and constraints of large-scale generative language models. Here are some secondary use cases we believe are

GPT-2 model card Last updated: November 2019 Inspired by Model Cards for Model Reporting (Mitchell et al.) , we’re providing some accompanying information about the GPT-2 family of models we're releasing. Model Details. This model was developed by researchers at OpenAI to help us understand how the capabilities of language model capabilities scale as a function of the size of the models (by parameter count) combined with very large internet-scale datasets (WebText). Model date February 2019, trained on data that cuts off at the end of 2017. Model type Language model Model version 1.5 billion p

related reading