jsekamane comments

Repositories
Issues
Comments

Results 2 comments of


                                            jsekamane

Write out a companion README style Markdown file for every processed table

How about using the [data package scheme](https://frictionlessdata.io/specs/data-package/)?

Proposal: use distributed network for training

I think distributed pre-processing would work great for specific elements, such as the “execution of API calls”-step in ToolFormer. You could: 1. centrally sample the API calls using the LM...