| license: apache-2.0 | |
| Checkpoints for https://huggingface.co/keeeeenw/Llama-3.2-1B-Instruct-Open-R1-Distill | |
| I am keeping it in a separate repo to improve the download speed for the original repo. | |
| This is useful for folks who want to probe into the process of how an LLM learns to reason or continued training for this model. |