Pinned Loading
-
-
-
-
-
-
gpt2-repro
gpt2-repro PublicA from-scratch GPT-2 reproduction: model, FineWeb tokenization pipeline, and a pretraining loop with gradient accumulation, bf16 autocast, cosine LR schedule and W&B logging.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.



