I finetuned 1.5B Qwen to near GPT-4o level bash generation perf

Show HN: I finetuned 1.5B Qwen to near GPT-4o level bash generation perf

Based, I finetuned 1.5B Qwen to near GPT-4o level bash generation perf works in show hn launch.

Profile

Purely a hobby side project to see how far I can push a really small model, using (mostly) automated training pipelinesOriginal mention: https://news.ycombinator.com/item?id=49869735There were a bunch of requests to release it. Full synthetic data: https://huggingface.co/datasets/dirac-run/ec-training-dataModels: https://huggingface.co/dirac-run/ec-1.5b-gguf and https://huggingface.co/dirac-run/ec-0.6b-ggufCli https://github.com/dirac-run/ecfeel free to train/use the data as you wish.

The company sits in the show hn launch segment, where it competes on its core product or service.

It is recorded at the Show HN launch stage.

Website: dirac.run/posts/easycommand