奇哥AI财经

About the monotonicity of bins.

2

Normally，it is essential for the bins besides missing to be monotonically increasing or decreasing on the badrate for better explainability. For exmple， the bigger a certain feature X1，the better chance...

想请教下, Squeeze论文里面准确率比较的那些其他方法是如何实现的？

1

您好： 如题 IDice和Apriori似乎不是精准匹配这个问题，把这两个用过来似乎是不是需要一些特殊技巧； R-Adtributer按照原本他论文的方法不太容易得出形如A，B数据集这种形式的结果； HotSpot好像没有开源; 这些都在Squeeze论文里面计算出来了在A,B数据集上的f1-score。 请问下可否分享一下实现方式，或者开放代码。

How to train my own image-text-pairs to enabling minigpt4 to classify new objects？

1

First, thanks for your great work and kindly open source to the public community! I have a dataset that contains various characters of a specific game. Obviously, these game characters...

[Question]: chatAquila-7B怎么设置单机多卡部署

2

### Description 如题 ### Alternatives _No response_

[BUG]: 上传知识库问答但是LLM的回答却是原生的，没有参考到知识库、

6

在新增知识库问答里面上传了一个.txt文档，然后问答，后台看到是定位到了这个.txt里的文章.也生成相应prompt传到了llm，但是llm的回答就是原生的回答。

Why Segment Embedding number only 3?

1

``` import torch.nn as nn class SegmentEmbedding(nn.Embedding): def __init__(self, embed_size=512): super().__init__(3, embed_size, padding_idx=0) ``` This is the source code. First idx is padding, thus only 2 segment is supported. Why...

Category features support

2

Only dataframe object is supported for the "fit" method ``` xgbse_model = XGBSEKaplanTree(PARAMS_TREE) # X = xgb.DMatrix(X, enable_categorical=True) xgbse_model.fit(X, y) ``` but enable_categorical is not set "True" in the source...