---
license: mit
datasets:
- HuggingFaceFW/fineweb
---

This is [karpathy's](https://github.com/karpathy) model from [the llm.c project](https://github.com/karpathy/llm.c/discussions/580) converted to HF format to investigate [bfloat16 performance](https://github.com/karpathy/llm.c/pull/571). 

The training run was 150B tokens, 1.5 epochs over the 100B FineWeb sample dataset.

There's active work underway at [https://github.com/karpathy/llm.c](https://github.com/karpathy/llm.c) so I'd suggest following the developments there!