SearchQwen2.5-7B is a compact Search Agent model from the Alibaba Cloud PAI team. It is trained with environment-aligned, solver-verified search trajectories generated by EasyDistill 2.0, and is designed for multi-hop search, browsing, and evidence integration. > SearchQwen2.5-7B 是基于 EasyDistill 2.0 环境对齐轨迹蒸馏链路训练的 Search Agent 小模型，支持结构化 search / browse 工具调用。 LLM-judge accuracy (%). Multi-hop QA averages 2WikiMultiHopQA, Bamboogle, HotpotQA, and MuSiQue; Deep Search averages GAIA, WebWalkerQA, xbench-deepsearch, and BrowseComp-ZH. The model returns a structured `; execute the tool, append its response, and continue until a final answer is produced. An external search/browse backend is required. This model follows the license included in this repository and the terms of its base model. Checksums are provided in SHA256SUMS.
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: alibaba-pai
Теги: qwen2, search-agent, tool-use, function-calling, deep-search, qwen, conversational, en
Лайков: 3 | Загрузок: 56
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
