AIMS2025/DeepSignal - Каталог нейросетей
Генерация текста

AIMS2025/DeepSignal

Добавлено:
AIMS2025/DeepSignal

DeepSignal is our suite of fine-tuned large language models for traffic-signal control. The current releases include three models: — DeepSignal-Phase-4B-V1 — next signal-phase prediction (predicts which phase to activate next and for how long) — DeepSignal-CyclePlan-4B-V1 — signal-cycle timing optimization (outputs green-time allocation for every phase in the upcoming cycle) — DeepSignal-CyclePlan-4B-V1.2 — updated CyclePlan release with stronger executable timing-plan generation, faster response, and improved queue/delay behavior All models are available on Hug Currently, this repository does not include the code for fine-tuning the large language model. — Team name: AIMSLab — Team members: Feng Xiao, Da Lei, Lu Li, Yuzhan Liu, Jinyou Chi, Yabang Wang. (Thanks Minyu Shen and Dapeng Zhang, for their contribution in the real-world…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: AIMS2025
Теги: gguf, qwen3, llama.cpp, lmstudio, traffic-signal-control, traffic-optimization, simulation, en
Лайков: 3  |  Загрузок: 2

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.