LiuJinzhe-Keepgoing

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation:

2

Thank you for your exciting work! But when I was running the GAN model, I encountered a problem. ———————————————————————— Start training... [W python_anomaly_mode.cpp:104] Warning: Error detected in AddmmBackward. Traceback of...

关于数据集和Plan和Tool指标的问题

1

哈喽，感谢您们精彩的工作！我认为这是十分有意义的。但是我有几个困惑。 我理解针对于Kagent这个框架，数据集中"type": "plantooluse"是为了验证模型的plan多步骤能力。但是： 1. golden_result_list中的json数据没有step的概念，看起来是没有先后执行顺序的。这个怎么作为多步骤推理的标签呢？ 模型在执行多次plan的时候，怎样选择golden_result_list的结果作为标准的label 2. 评价指标中的Planning和Tool-use是否评价的是一次plan的过程，这样能否体现多步骤推理的能力呢？ 感谢！ 并且期待您的回复！ 谢谢！

multi-step operations

1

Hi, thank you very much for your interesting work! I have a question, how does LLM perform a series of web page operations after judging the location of the element...

function of these parameters

1

Very valuable job, I'm preparing to follow him, but I'm in some trouble. Can you explain in detail the specific implementation steps of transforming hml3d dataset or standard SMPL format...