Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix and rework GPT-TF.js #807

Draft
wants to merge 10 commits into
base: develop
Choose a base branch
from
Draft

Fix and rework GPT-TF.js #807

wants to merge 10 commits into from

Conversation

JulienVig
Copy link
Collaborator

Addresses #654

  • Fix weight initialization from zero to random uniform
  • Implement weight sharing between token embeddings and the language modeling head
  • Improve generation with top k sampling option
  • Add seed for deterministic runs
  • Implement text loaders by byte chunk rather than by line which doesn't require to pad each line to the context length

@JulienVig JulienVig self-assigned this Oct 16, 2024
…Loaders now yield token sequences of length blockSize
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.

1 participant