nanogpt
https://github.com/karpathy/nanogpt
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
not yet supported1 Subscribers
Add a CodeTriage badge to nanogpt
Help out
- Issues
- Apple Silicon M1
- Is graph card required?
- Reproducing GPT-2 results on M1 Mac
- Why load batches from random positions? Why not sequential?
- Loss calculation
- Newbie Q: does the training data (train_ids) has to be consecutive? can I inject -1 as the integer marker id into train_ids?
- To reduce GPU memory usage & found a bug
- Sample from a subset of the token_embedding_table
- dropout is 0.0
- Torch >= 2.2.0 inference issues on MPS
- Docs
- not yet supported