Can anyone answer some questions on how GPT-NeoX-20B was developed, and future models?

• the-pile

  15 1,403 0.0 Python
  

For example, before this I didn't realize one of the sources of data that the pile uses is a massive number of emails gathered during the Enron lawsuits. Weird, but cool I guess.

• DALLE-mtf

  41 435 0.0 Python

  Open-AI's DALL-E for large scale training in mesh-tensorflow.

  

Eleuther AI, creator of Neo 2.7B (Calliope), GPT-J 6B (Sigurd), NeoX 20B (Krake), and play a key role in the making of Stable Diffusion. They are at the very core of open-source machine learning, NAI devs have very close relationship to them, well, part of the group, I guess. They are the one who get the compute.

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project