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
- fix: properly handle MPS device type for Apple Silicon training
- security: use restricted unpickler for meta.pkl to prevent code execution
- feat: add optional Attention Residuals (Block AttnRes) architecture
- Add KV cache to generate, unify forward pass
- Scalar C++ Transformer Implementation — Verified Against PyTorch
- fix: ZeroDivisionError in get_lr when lr_decay_iters == warmup_iters
- Regarding your LLMOS concept
- Add uv support and update README for modern environment management
- Why not just surpass 5.2 directly? Let's add the LiE enhancement plugin.
- Meet TrueNanoGPT
- Docs
- not yet supported