shibing624/text2vec

Issues

• 在跑第二段示例代码时遇到的警告：FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. warnings.warn(

  #151 opened 8 months ago by Phoenix233333
  3

• cannot import name 'Similarity' from 'text2vec' (/root/text2vec.py)

  #156 opened 3 months ago by smileyboy2019
  1

• 是否支持ollama

  #155 opened 3 months ago by smileyboy2019
  1

• 能否在文档说下 text2vec.SentenceModel 和 SentenceTransformer 到底有什么区别？

  #154 opened 4 months ago by qiulang
  5

• 我该如何指定模型所在的位置，这样就不用到Hugging Face下载了

  #153 opened 5 months ago by omaiyiwa
  2

• loss function

  #152 opened 8 months ago by riyajatar37003
  4

• 向量降维

  #149 opened 8 months ago by ann22
  1

• 1024 维度的模型在哪找呢

  #150 opened 8 months ago by wmvm0
  0

• input.txt 文件是什么格式？

  #148 opened a year ago by DokiDoki1103
  1

• 训练的loss一直为0，请问这是怎么回事

  #146 opened a year ago by ann22
  6

• 关于BGE 微调疑问

  #125 opened a year ago by CuteMing
  2

• 对于模型微调的疑问

  #134 opened a year ago by cjji
  2

• 关于spearman评估方法的疑问

  #133 opened a year ago by hellopahe
  2

• 执行sim.get_score("hello","hello") 报错。

  #147 opened a year ago by melisa81
  1

• text2vec中，关于token与汉字字符换算

  #145 opened a year ago by cutelitchi
  1

• 请教bge用自己数据微调的问题

  #144 opened a year ago by LanceLuoyuan
  3

• 相似度問題。

  #142 opened a year ago by chunnan6666
  1

• examples/gradio_demo.py

  #136 opened a year ago by realnghon
  1

• 代码疑问：矩阵计算batch内的cos loss

  #143 opened a year ago by CathyKitten
  1

• 模型微调问题

  #141 opened a year ago by CathyKitten
  3

• 关于模型的选择

  #140 opened a year ago by Xiao-congxi
  2

• text2vec-base-multilingual 向量维度可以从 384 调整到 768 吗

  #138 opened a year ago by dingcb
  2

• 模型微调卡住

  #139 opened a year ago by CathyKitten
  1

• 关于BGE的蒸馏问题

  #137 opened a year ago by hgwu4869
  2

• CoSENT损失计算问题

  #135 opened a year ago by YingchaoX
  2

• 本开源框架是否支持基于模型：GanymedeNil/text2vec-large-chinese + 私有数据 进行微调训练

  #132 opened a year ago by mininggold007
  1

• 多进程encode无法正常运行

  #131 opened a year ago by imempty
  2

• 想问一下，simcse是不是就是sbert

  #129 opened a year ago by TanXiang7o
  2

• v1.2.0优化细节咨询

  #130 opened a year ago by MingFL
  2

• triton server Deployment

  #122 opened a year ago by gaoyuan5251
  1

• 能否测试LLM大规模语言模型计算出的text vector 是否能大幅度提高语义匹配的精度

  #128 opened a year ago by doptime
  1

• 如何使用多卡进行im_model.model.encode()

  #126 opened a year ago by newbietuan
  7

• 使用命令运行training_sup_text_matching_model_mydata.py脚本报错You have to specify either input_ids or inputs_embeds

  #124 opened a year ago by 1006076811
  13

• 训练数据

  #127 opened a year ago by HaoRenkk123
  1

• 测评结果

  #118 opened a year ago by Elisewyh
  2

• 模型离线使用

  #116 opened a year ago by Huanyongji
  2

• loss反向传播全0

  #120 opened a year ago by rangehow
  4

• 你好，我跑了这个文件training_sup_text_matching_model_jsonl_data为啥报错呢

  #123 opened a year ago by aslick
  3

• 小白求问

  #121 opened a year ago by xuyang20232333
  1

• Text Matching task: error: unrecognized arguments: --fp16

  #119 opened a year ago by rangehow
  1

• 标题图片显示不正常

  #117 opened a year ago by peilongchencc
  1

• 您好，在使用training_sup_text_matching_model_en.py进行微调的时候遇到的一些问题

  #106 opened a year ago by Fino2020
  6

• 使用中发现单机8卡的训练速度比sentense-transformer的速度慢。

  #114 opened a year ago by sangyongjia
  5

• 指标如何评判好坏

  #107 opened a year ago by KekeWa
  3

• 转ONNX后，出现问题，求解答

  #115 opened a year ago by dtMndas
  1

• 关于cosnet中loss的不解

  #112 opened a year ago by lightislost
  0

• The difference between STSB and STSBenchmark

  #111 opened a year ago by staoxiao
  1

• Loss稳定在较高数值不再下降，无法复现效果

  #113 opened a year ago by Mike4Ellis
  3

• AutoTokenizer保存ernie3.0失败

  #110 opened a year ago by yuankunW
  1

• 如何开启多卡训练？

  #109 opened a year ago by sangyongjia
  2