Flags likely secrets the deterministic scanner MISSED (false negatives). This repo contains a PEFT LoRA (r=16, alpha=32) for Qwen/Qwen3.6-35B-A3B, used by Droid Shield 2.0. It targets the base text tower and must be applied on top of the base weights; it is not a standalone model. This adapter was trained against an exact prompt and I/O schema. Sending anything else may degrade it silently. All three pieces below are part of the trained-model contract. Send the contents of system-prompt.txt verbatim as the system message. The exact bytes matter. — sha256(system-prompt.txt) = d475080b8357748aa5c18853cb89b528a85547dae8df07559ae94bf58fcaa164 Caveat: the shipped system prompt intentionally refers to «Droid Shield» because these adapters were trained for Factory’s Droid Shield workflow. Customers repurposing the adapter may want different branding or framing; validate any prompt edits because changing the trained contract can change scores. A single JSON object, serialized as pretty-printed JSON with 2-space indentation and non-ASCII preserved (canonical form: JS JSON.stringify(value, null, 2)), with these keys: — extension: the file extension — lines: a small ordered window of source…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: factoryai
Теги: peft, qwen3_5_moe, lora, droid-shield, secret-detection, conversational
Лайков: 3 | Загрузок: 22
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
