Skip to content

gpt2, from scratch #11

Open
Open
@leonlenk

Description

@leonlenk
  • In week 7 we implmented the full transformer, but it was actually just the gpt2 model
  • In this notebook we load the gpt2 model weights into the full transformer and see how it preforms

Metadata

Metadata

Assignees

Labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions