Memory Operator is a sub-model exclusive to MemOS, designed specifically for memory operations. Its core functionalities include processing memory extraction, integration, and updating. The purpose of building the Memory Operator sub-model is: 1. Support local-only deployment, making it convenient to use MemOS in restricted environments (e.g., scenarios where internet access is unavailable). 2. Perform memory operations at lower cost and higher speed, while maintaining strong system performance. The first Memory Operator model is MemReader-4B, which is derived from a fine-tuned version of Qwen3-4B. It has been further trained using supervised fine-tuning on both human-annotated and model-generated data, achieving high performance in memory extraction tasks. — Type: Causal Language Models — Training Stage: Supervised Finetune — Supported Languages: en, zh — Number of Parameters: 4B — Context Length: 32,768 Evaluation results on Locomo using memories extracted by different models in MemOS: By replacing your open-source model with MemReader-4B, you can achieve the same memory extraction performance while saving over 70% in resource consumption (4B vs 14B)! You can also directly load…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: MemTensor
Теги: qwen3, conversational, en, zh, text-generation-inference, endpoints_compatible
Лайков: 4 | Загрузок: 12
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
