{"slug": "show-hn-i-finetuned-1-5b-qwen-to-near-gpt-4o-level-bash-generation-perf", "title": "Show HN: I finetuned 1.5B Qwen to near GPT-4o level bash generation perf", "summary": "A developer released ec-1.5b-gguf and ec-0.6b-gguf, two finetuned Qwen models, along with the full synthetic training dataset at huggingface.co/datasets/dirac-run/ec-training-data and a CLI at github.com/dirac-run/ec, claiming the 1.5B model reaches near GPT-4o-level bash generation performance. The project was built as a hobby side project using mostly automated training pipelines, and the developer says the data may be freely used for training.", "body_md": "Purely a hobby side project to see how far I can push a really small model, using (mostly) automated training pipelines\n\nOriginal mention: [https://news.ycombinator.com/item?id=49869735](https://news.ycombinator.com/item?id=49869735)\n\nThere were a bunch of requests to release it. Full synthetic data: [https://huggingface.co/datasets/dirac-run/ec-training-data](https://huggingface.co/datasets/dirac-run/ec-training-data)\n\nModels: [https://huggingface.co/dirac-run/ec-1.5b-gguf](https://huggingface.co/dirac-run/ec-1.5b-gguf) and [https://huggingface.co/dirac-run/ec-0.6b-gguf](https://huggingface.co/dirac-run/ec-0.6b-gguf)\n\nCli [https://github.com/dirac-run/ec](https://github.com/dirac-run/ec)\n\nfeel free to train/use the data as you wish.\n\nComments URL: [https://news.ycombinator.com/item?id=49966238](https://news.ycombinator.com/item?id=49966238)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-i-finetuned-1-5b-qwen-to-near-gpt-4o-level-bash-generation-perf", "canonical_source": "https://dirac.run/posts/easycommand", "published_at": "2026-10-05 15:35:29+00:00", "updated_at": "2026-10-05 15:49:30.914312+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "developer-tools", "ai-research"], "entities": ["Qwen", "dirac-run", "ec-1.5b-gguf", "ec-0.6b-gguf", "Hugging Face", "GitHub", "GPT-4o"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-i-finetuned-1-5b-qwen-to-near-gpt-4o-level-bash-generation-perf", "markdown": "https://wpnews.pro/news/show-hn-i-finetuned-1-5b-qwen-to-near-gpt-4o-level-bash-generation-perf.md", "text": "https://wpnews.pro/news/show-hn-i-finetuned-1-5b-qwen-to-near-gpt-4o-level-bash-generation-perf.txt", "jsonld": "https://wpnews.pro/news/show-hn-i-finetuned-1-5b-qwen-to-near-gpt-4o-level-bash-generation-perf.jsonld"}}