This is a highly optimized, lightweight (270M parameters) function-calling model fine-tuned on top of google/functiongemma-270m-it. It is specifically designed to run on-device (locally) as a pre-flight search and routing assistant for the Elixir-native Beamcore agent harness. In agentic software engineering workflows, sending large workspace structures, complete file contents, and extensive tool schemas to massive frontier models is slow, expensive, and leads to context pollution. beamcore/tools solves this by running locally to perform pre-flight search routing: 1. Analyze Intent: When a user issues a request, beamcore/tools determines whether search/traversal tools are needed to gather codebase context. 2. Execute Tools: If context is missing, it emits structured tool calls (e.g., glob, grep, tree, read) to fetch local file structures or code. 3. Minimize Tokens: If no tools are required (or after search tools run and collect the necessary files), the main reasoning model is invoked with a minimal, relevant context, drastically reducing token overhead and billing. The model is fine-tuned to work with the following four workspace-inspection tools: Find workspace files matching a…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: beamcore
Теги: gemma3_text, agent, tool-use, function-calling, on-device, beamcore, sft, trl
Лайков: 3 | Загрузок: 18
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
