huggingface config_error ai_generated true

ValueError: The task `text-generation` is not supported by the pipeline for this model. Supported tasks are: ['feature-extraction', 'fill-mask', 'sentence-similarity', 'text-classification'].

ID: huggingface/pipeline-task-unavailable

Also available as: JSON · Markdown · 中文
95%Fix Rate
90%Confidence
1Evidence
2023-11-01First Seen

Version Compatibility

VersionStatusIntroducedDeprecatedNotes
transformers 4.36.0 active — — —
huggingface-hub 0.20.0 active — — —
Python 3.11 active — — —

Root Cause

The pipeline is configured with a task that the model's architecture cannot perform, often because the model is an encoder-only type (e.g., BERT) but the task is decoder-only (e.g., text generation).

generic

中文

pipeline配置的任务是模型架构无法执行的，通常因为模型是仅编码器类型（如BERT），但任务是仅解码器类型（如文本生成）。

Official Documentation

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

Workarounds

  1. 95% success Use a model that supports the desired task. For text generation, use a decoder-only model like GPT-2: `pipeline('text-generation', model='gpt2')`. Check the model card on Hugging Face Hub for supported tasks. 
    Use a model that supports the desired task. For text generation, use a decoder-only model like GPT-2: `pipeline('text-generation', model='gpt2')`. Check the model card on Hugging Face Hub for supported tasks.
  2. 90% success If you must use the current model, choose a supported task. For example, for BERT: `pipeline('text-classification', model='bert-base-uncased')`. 
    If you must use the current model, choose a supported task. For example, for BERT: `pipeline('text-classification', model='bert-base-uncased')`.

中文步骤

  1. 使用支持所需任务的模型。对于文本生成，使用仅解码器模型如GPT-2：`pipeline('text-generation', model='gpt2')`。在Hugging Face Hub上查看模型卡片以了解支持的任务。
  2. 如果必须使用当前模型，选择支持的任务。例如，对于BERT：`pipeline('text-classification', model='bert-base-uncased')`。

Dead Ends

Common approaches that don't work:

  1. 95% fail

    BERT is an encoder-only model; it lacks a language modeling head for generation, so forcing the task will cause runtime errors or produce gibberish.

  2. 70% fail

    The error is about model-task compatibility, not library version; a newer version won't make BERT generate text.