This checkpoint is based on Qwen/Qwen3-1.7B and is prepared for the CS-552 2026 safety benchmark submission. — Starting model: Qwen/Qwen3-1.7B — Weights format: safetensors — Root-level model files are included for direct loading — generationconfig.json is included — chattemplate.jinja is included — Thinking mode is forced OFF in the chat template The tokenizer chat template injects a safety-classification system prompt and requires the model to answer with exactly one boxed label: The generation prompt includes the empty Qwen3 non-thinking stub:
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: cs-552-2026-ChatMODS
Теги: qwen3, safety, content-moderation, cs-552, conversational, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 62
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
