huggingface config_error ai_generated true

ValueError: The task `summarization_v2` is not supported by the pipeline. Supported tasks are: ['text-classification', 'token-classification', 'question-answering', 'summarization', 'translation', 'text-generation', 'zero-shot-classification', 'fill-mask']

ID: huggingface/pipeline-task-not-supported

Also available as: JSON · Markdown · 中文
95%Fix Rate
82%Confidence
1Evidence
2023-08-20First Seen

Version Compatibility

VersionStatusIntroducedDeprecatedNotes
transformers>=4.20.0 active — — —
python>=3.7 active — — —

Root Cause

The pipeline task name is misspelled or does not exist in the supported task list, often due to a typo or using an outdated task identifier.

generic

中文

pipeline 任务名称拼写错误或不在支持的任务列表中，通常是由于拼写错误或使用了过时的任务标识符。

Official Documentation

https://huggingface.co/docs/transformers/main/en/main_classes/pipelines

Workarounds

  1. 95% success Use the correct task name from the supported list. Example: pipe = pipeline('summarization', model='facebook/bart-large-cnn') 
    Use the correct task name from the supported list. Example: pipe = pipeline('summarization', model='facebook/bart-large-cnn')
  2. 85% success Check the model's config for the correct task: model.config.task_specific_params or use AutoModelForSeq2SeqLM for summarization. 
    Check the model's config for the correct task: model.config.task_specific_params or use AutoModelForSeq2SeqLM for summarization.

中文步骤

  1. 从支持列表中使用正确的任务名称。示例：pipe = pipeline('summarization', model='facebook/bart-large-cnn')
  2. 检查模型配置以获取正确任务：model.config.task_specific_params 或使用 AutoModelForSeq2SeqLM 进行摘要。

Dead Ends

Common approaches that don't work:

  1. 80% fail

    Pipeline tasks are predefined; custom tasks require subclassing and registering.

  2. 70% fail

    Task names must exactly match the supported list; 'text2text-generation' is not a valid pipeline task.