A 26.3M-parameter Cactus Needle fine-tune for routing coding-agent intents into Pi’s four built-in tools: read, bash, edit, and write. It is designed as a small parser/router, not a knowledge engine. An upstream planner should provide concrete paths, commands, content, or replacements; this model selects the tool and copies those arguments into a structured call. Evaluation used a held-out, balanced 40-example test set with 10 examples per tool. Exact matches by tool improved from read 8/10, bash 2/10, edit 0/10, write 1/10 to read 9/10, bash 8/10, edit 9/10, write 6/10. These are local single-run measurements, not an external benchmark. See metrics.json for machine-readable results. — Base: Cactus-Compute/needle — Examples: 1,500 (bash: 450; read, edit, write: 350 each) — Split: 1,420 train / 40 validation / 40 test — Epochs: 1 — Batch size: 32 — Training steps: 22 — Optimizer learning rates: Adam 3e-5, Muon 0.02 — Checkpoint-selection validation exact match: 70.0% — Synthetic-data generator: Codex CLI, with strict schema, grounding, and deduplication validation The additional bash data emphasizes parsing fully specified arbitrary shell commands, including quoting, flags,…
Модальности:
Генерация текста
Области применения:
Вызов функций (Tool use)
Задача: Генерация текста
Автор: theabbie
Теги: jax, custom, needle, function-calling, tool-use, coding-agent, pi-coding-agent, flax
Лайков: 4 | Загрузок: 622
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
