Skip to content

Added wikitext task, added text-dataset for core, node and web, renamed task.taskId to task.id#619

Closed
peacefulotter wants to merge 4 commits intoepfml:NAN-llm-s314cyfrom
peacefulotter:text-dataset
Closed

Added wikitext task, added text-dataset for core, node and web, renamed task.taskId to task.id#619
peacefulotter wants to merge 4 commits intoepfml:NAN-llm-s314cyfrom
peacefulotter:text-dataset

Conversation

@peacefulotter
Copy link
Copy Markdown
Collaborator

This PR contains the implementation of the text-dataset which includes a core text dataset and the corresponding web+node versions that extend it.
This PR also includes the wikitext task, a text task for LLMs, where getModel returns a GPT tf.LayersModel instance.
Note: #618 is required for this PR to work

…itext task. Provided downloading dataset scripts for wikitext and tiny-shakespeare (may be supported later) and documentation in the README
@martinjaggi martinjaggi mentioned this pull request Feb 28, 2024
@tharvik tharvik mentioned this pull request Feb 29, 2024
@tharvik tharvik self-assigned this Mar 7, 2024
tharvik pushed a commit that referenced this pull request Mar 13, 2024
tharvik pushed a commit that referenced this pull request Mar 15, 2024
tharvik pushed a commit that referenced this pull request Mar 18, 2024
@tharvik tharvik closed this in cb27570 Mar 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants