Compact, instruction-finetuned code generation model built on Qwen2.5-Coder-0.5B-Instruct. Fast local code completion with minimal resources. — 500M parameters — runs on CPU, MPS, or low-VRAM GPU — 80% pass rate on HumanEval (16/20 tasks) — Apache 2.0 — fully open, commercially usable — CLI-ready — plug into arche-code The CLI auto-downloads the model on first use. Full docs: github.com/OpenSynapseLabs/arche-code — Lead magnet — free, capable entry point into the Arche ecosystem — Edge-friendly — runs on laptops, Raspberry Pi, mobile devices — Real code — generates executable Python, not just snippets — A replacement for 7B+ models on complex architecture tasks — A chat model — instruction-tuned for code generation only — The final word — larger Arche coding models are shipping this month — Struggles with multi-step reasoning (e.g., LRU Base model: Qwen2.5-Coder-0.5B-Instruct (Apache 2.0).
Модальности:
Генерация текста
Области применения:
Генерация кода Дополнение кода Программирование Следование инструкциям Диалог / чат Вызов функций (Tool use)
Языки программирования:
Python
Задача: Генерация текста
Автор: opensynapselabs
Теги: qwen2, code, code-generation, code-completion, code-llm, python, programming, developer-tools
Лайков: 4 | Загрузок: 70
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
