Repository navigation
Add Tiny Shakespeare language modeling task - #1244
Merged
Merged
Conversation
ale18V
force-pushed
the
feat/issue-1243-shakespeare
branch
from
October 3, 2026 11:06
bfec464 to
d1faf8d
Compare
ale18V
marked this pull request as ready for review
October 3, 2026 11:13
ale18V
added this pull request to stack #1245
October 3, 2026 11:14
ale18V
force-pushed
the
feat/issue-1243-shakespeare
branch
from
October 5, 2026 16:05
d1faf8d to
ee4317a
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What & why
Add Tiny Shakespeare as a lightweight text corpus for language-model experiments (Closes #1243). A new decentralized GPT task links to the ~1 MiB corpus, and
datasets/populatedownloads it for local use. Downloaded data is ignored by Git, following DISCO's existing dataset convention.Technical plan
Register the Shakespeare task and GPT model card, using the existing GPT-2 tokenizer with context length 64, batch size 8, and one training epoch. Use the upstream Tiny Shakespeare download for both the task's sample link and the dataset setup script. The download was verified against the corpus checksum; package and server builds and task serialization tests passed.
Deviations from plan
None.
Todo
None.