LoRA Speedrun public leaderboard: 6 min 05 sec fine-tune Qwen2.5-1.5B to 61.1% accuracy on GSM8K

AI Brief

![Image 1: CI](https://github.com/Saivineeth147/lora-speedrun/actions/workflows/ci.yml)![Image 2: License: MIT](https://github.com/Saivineeth147/lora-speedrun/blob/main/LICENSE)![Image 3: PRs Welcome](https://github.

Return to original text

A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.

Open github.com original