Show HN: I finetuned 1.5B Qwen to near GPT-4o level bash generation perf https://ift.tt/7sHVNSx
Show HN: I finetuned 1.5B Qwen to near GPT-4o level bash generation perf Purely a hobby side project to see how far I can push a really small model, using (mostly) automated training pipelines Original mention: https://ift.tt/QT7yDEB There were a bunch of requests to release it. Full synthetic data: https://ift.tt/0KsFr73 Models: https://ift.tt/rH01M6q and https://ift.tt/iQFpTr1 Cli https://ift.tt/z3QJmp0 feel free to train/use the data as you wish. https://ift.tt/Nr8e9l1 October 5, 2026 at 10:35PM
Komentar
Posting Komentar