issues
search
shibing624
/
text2vec
text2vec, text to vector. 文本向量表征工具,把文本转化为向量矩阵,实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型,开箱即用。
https://pypi.org/project/text2vec/
Apache License 2.0
4.39k
stars
392
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
对称语义还是非对称语义?
#103
yufengzhe1
closed
1 year ago
2
"闵可夫斯基距离"错误
#102
marlo-Li
closed
1 year ago
1
text2vec-base-chinese-sentence cpu推理速度慢 正常吗
#101
Dengyingjie
closed
1 year ago
2
添加Bfloat16和多卡DataParallel训练功能
#100
wptoux
closed
1 year ago
1
您好!我想请问一下关于数据集的构建
#99
programmeguru
closed
1 year ago
1
文件的分割,text2vec-base-chinese支持最大输入tokens是128
#98
stoneLee81
closed
1 year ago
2
训练数据正负样本的比例
#97
baisuzi
closed
1 year ago
1
text2vec-base-chinese模型最大支持多少输入tokens
#96
stoneLee81
closed
1 year ago
2
请问有没有抽取关键词的模型
#95
Godlikemandyy
closed
1 year ago
1
我按照100个batch进行一次eval_model,发现和原来的结果不同
#94
programmeguru
closed
1 year ago
5
AttributeError: ''NoneType object has no attribute 'squeeze'
#93
sz2three
closed
1 year ago
5
Question about training sample
#92
callanwu
closed
1 year ago
4
请问无监督的训练数据是如何构建的呢 examples/training_unsup_text_matching_model_en.py
#91
sz2three
closed
1 year ago
1
m芯片使用cpu的模式也会出现Torch not compiled with CUDA enabled’的错误
#90
stoneLee81
closed
1 year ago
2
有跟openAI ada embedding做比较吗
#89
CopyNinja1999
closed
1 year ago
1
为什么训练集不能shuffle呢,shuffle之后效果下降很多
#88
programmeguru
closed
1 year ago
3
为什么不对 embedding 做归一化呢?
#87
thsno02
closed
1 year ago
2
text2vec-base-chinese-paraphrase模型相似度计算问题
#86
zaczou
closed
1 year ago
1
w2v-light-tencent-chinese对文本是否有长度限制呢?
#85
graciechen
closed
1 year ago
1
能用新闻分类的数据集做训练微调吗
#84
TanXiang7o
closed
11 months ago
4
为什么我没有找到SOTA的指标,release model表格里没有比中文表格里指标大的啊
#83
TanXiang7o
closed
1 year ago
1
semantic_search结果变化
#82
xxllp
closed
1 year ago
0
text2vec仅仅是预训练模型将文本表示出向量吗?
#81
1264561652
closed
1 year ago
3
支持日文吗?
#80
sz2three
closed
1 year ago
2
有没有可能用较好7B中文预训练模型来contrasive train出一个s2p或p2p的embedding模型?
#79
firezym
closed
1 year ago
2
在真实场景中,效果最好的还是text2vec-base-chinese
#78
danger-dream
closed
1 year ago
6
请问怎么才能用GPU来推理,我采用.cuda 发现 SentenceModel 没有cuda 这个属性
#77
wlhonce
closed
1 year ago
1
无法稳定使用cuda加速推理
#76
livehl
closed
1 year ago
4
请问下如果试用 faiss保存这个里面的耗时的embedding应该怎么写,能给个示例吗
#75
xx-zhang
closed
1 year ago
0
should i articiple while embedding chinese
#74
abusizhishen
closed
10 months ago
1
请问如何导出完整的模型
#73
MingFL
closed
1 year ago
5
cos 值的疑惑
#72
hanswang73
closed
1 year ago
8
运行 api server: python jina_server_demo.py报错 ModuleNotFoundError
#71
alexhmyang
closed
11 months ago
2
label能否支持多档位呢[Feature] <title>
#70
MingFL
closed
1 year ago
2
关于测评结果
#69
1264561652
opened
1 year ago
5
中文匹配数据集的评测结果中的模型可以在哪里下载呢?
#68
DSXiangLi
closed
1 year ago
2
关于模型评估
#67
AceCoder0
opened
1 year ago
2
是否可以商用?
#66
bh4ffu
closed
1 year ago
1
sbert英文stsb数据集上10个epoch皮尔森系数只有0.63
#65
LemonMi
closed
1 year ago
4
使用您的 shibing624/text2vec-base-chinese 模型,输出的词嵌入是768维的,能降低维度吗?比如128维
#64
JonGates
closed
1 year ago
1
目前哪种句子向量与篇章向量比较sota
#63
yuanjie-ai
closed
1 year ago
3
服务器不能下载模型文件,请问可以手动上传那几个模型文件吗,上传到哪里呢
#62
zhaoyiCC
closed
1 year ago
2
能在更多样本训练更准的模型吗
#61
alexw994
closed
1 year ago
10
调用m = CosentModel("bert-base-chinese") 试 总是killed
#60
zhaoyiCC
closed
1 year ago
4
自有数据集构建的疑问
#59
Gladiator566
closed
1 year ago
5
相关paper或基准
#58
1264561652
closed
1 year ago
2
what if the sentence is longer than BERT default 512 ?
#57
RedBlack888
closed
1 year ago
9
是否支持模型加速
#56
flydsc
closed
1 year ago
4
semantic_search速度的一点疑问
#55
xxllp
closed
1 year ago
6
长文本的相似度
#54
xxllp
closed
1 year ago
5
Previous
Next