Skip to content

issues Search Results · repo:thunlp/OpenPrompt language:Python

Filter by

261 results
 (76 ms)

261 results

inthunlp/OpenPrompt (press backspace or delete to remove)

Building wheels for collected packages: sentencepiece Building wheel for sentencepiece (setup.py) ... error error: subprocess-exited-with-error × python setup.py bdist_wheel did not run successfully. ...
  • z-x-x136
  • Opened 
    on Dec 5, 2024
  • #324

The new version of transformer==4.28.1 cannot use the .generate() function in text generation. The exception is: File ...\transformers\generation\utils.py , line 1210, in generate self._validate_model_class() ...
  • jzySaber1996
  • Opened 
    on Dec 5, 2024
  • #323

在读了贵作Prototypical Verbalizer for Prompt-based Few-shot Tuning 是个很好的文章,但是我比较好奇代码是怎么实现的,然后我需要定位到程序的运行入口在哪里,我找了半天,感觉是在项目的experiments/cli.py这个[文件]中。而这个文件是需要读取配置文件的,那么原型学习的配置文件是在experiments/classification_proto_verbalizer.yaml中。 ...
  • Charon-HN
  • Opened 
    on Nov 26, 2024
  • #322

The original code worked but had some inefficiencies and deviations from best practices. Here’s a quick list of issues addressed: Hardcoded Dependencies: Dependencies were embedded in the code, making ...
  • ady-31
  • Opened 
    on Nov 3, 2024
  • #321

在定义好之后classes和Dataset之后, 使用 from openprompt.plms import load_plm plm, tokenizer, model_config, WrapperClass = load_plm( bert , bert-base-cased ) 去加载预训练模型,报错显示: OSError: We couldn t connect to https://huggingface.co/ ...
  • shenjialiang
  • 1
  • Opened 
    on Oct 23, 2024
  • #319

Code: import numpy as np from sklearn.model_selection import KFold #import tensorflow as tf from sklearn import metrics from sklearn.metrics import accuracy_score from sklearn.metrics import f1_score ...
  • fengmingfeng
  • 6
  • Opened 
    on Jul 28, 2024
  • #316

hello, Thanks for providing the amazon repo. But I have a question regarding the loss function in tutorial /0_basic.py. The loss function is loss_func = torch.nn.CrossEntropyLoss() which applies the softmax ...
  • Juanhui28
  • Opened 
    on Jul 24, 2024
  • #315

I am getting this tokeniser `--- [86](vscode-notebook-cell:?execution_count=2 line=86) probabilities, predicted_labels = predict_medical_concept_relevance(metadata) [87](vscode-notebook-cell:?execution_count=2 ...
  • komi786
  • Opened 
    on Jun 15, 2024
  • #312

i tried to use latest version of openprompt (pip install openprompt and aslo tried by cloning from github) with transformer 4.41 and 4.42 b `oduleNotFoundError Traceback (most recent call last) Cell In[2], ...
  • komi786
  • 1
  • Opened 
    on May 18, 2024
  • #311

您好,OpenPrompt可以部署在中文预训练模型上来处理中文分类任务吗,例如plm, tokenizer, model_config, WrapperClass = load_plm(bert, chinese-roberta-wwm-ext)?在设计Template和ManualVerbalizer时有什么注意事项?
  • kalixim
  • 1
  • Opened 
    on May 14, 2024
  • #310
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub