Ziqi Yuan

Add BPE encoder

2

add the bytepair encoding [#7](https://github.com/PetrochukM/PyTorch-NLP/issues/7)

很好用的 template 对于将多个模型能够动态导入，但是，不同的模型往往具有不同的超参数组，这个如何实现动态切换呢？这个template 之前有考虑到么？是否需要一个类似于config_interface 的模块 @miracleyoo

This is a bug on xgboost.

2

**Description: XGBClassifier explainer failed when n_estimators=1.(extreme situation)** E.g. model_t = XGBClassifier(random_state=1111, max_depth=4, n_estimators=1) show_prediction(model, test_input[tougue_correct_q[0]]) will failed to run. **The error message is as follows:**

您好，请问一下： 1. 代码仓库的 https://github.com/inouye-lab/ShapleyExplanationNetworks/blob/cab6644677894f0ac88610d2f9cfca239068f403/ShapNet/shallow.py#L332 这里features 的计算公式怎么理解呢，len(list_modules)) 应该是所有 dim * (dim - 1) // 2。features 是否等于 dim 呢？按照现在的计算方法，在第二个实例代码中，features = int((1 + math.sqrt(32*31 / 2)) // 2) = 11 导致 len(keys) =...

Thanks for your great work of visualizing and understanding internal mechanics in multimodal models. However, there is still some concerns with regard to affective analysis topic. 1. Model simulation shows...