The larger sibling of nl2sh-1.5b: 1.9 GB, still CPU-only, and about 4 points more accurate at roughly half the speed. Turns a plain-English request into a single shell command. Qwen2.5-Coder-3B-Instruct with a LoRA fine-tune (r=32, α=64, all linear layers) on 125,770 natural-language/shell pairs, merged and quantized to GGUF Q4KM. Built for nl2sh but usable with any llama.cpp runtime. The 3B is +4.0 points more accurate, measured on the same 300 tasks, same stack, three repeats each — comfortably outside the noise floor. It costs 2.3× throughput and ~1.9× memory. Take the 1.5B for interactive use on a laptop; take this if accuracy matters more than latency. Measured on InterCode-ALFA, which scores a command by executing it in a container and comparing the resulting filesystem, file contents and stdout against a reference. A task passes only on an exact match, across 300 tasks. Fine-tuning is worth +0.090 on this base (0.567 → 0.657, p = 0.002 by exact McNemar on paired per-task outcomes). The model also beats an untuned 7B — a model 2.3× its size — by 4.4 points. Measured with the unmodified upstream scorer at temperature 0, 64-token budget, on all 300 tasks, using paired per-task…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Языки программирования:
Bash/Shell
Задача: Генерация текста
Автор: ThorOdinson246
Теги: gguf, shell, bash, command-generation, llama.cpp, en, endpoints_compatible, conversational
Лайков: 3 | Загрузок: 41
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
