← 模型广场
B
ByteDance: UI-TARS 7B
bytedance/ui-tars-1.5-7b
图像理解流式
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...
价格
输入
$0.1 / 1M
输出
$0.2 / 1M
参数
上下文
128,000 tokens
输入模态
image, text
输出模态
text
知识截止：2025-01-31
发布：2025-07
支持参数
frequency_penaltylogit_biasmax_tokenspresence_penaltyrepetition_penaltyseedstoptemperaturetop_ktop_p
开放权重 · HuggingFace
442,785 月下载
554 收藏
apache-2.0 image-text-to-text arXiv:2501.12326arXiv:2404.07972arXiv:2409.08264arXiv:2401.13919arXiv:2504.01382arXiv:2405.14573arXiv:2410.23218arXiv:2504.07981
在 HuggingFace 查看 →