huggingface config_error ai_generated true

ValueError: repetition_penalty 和 no_repeat_ngram_size 不能同时设置，因为它们可能会冲突。

ValueError: repetition_penalty and no_repeat_ngram_size cannot be set simultaneously as they may conflict.

ID: huggingface/transformers-generation-config-repeat-penalty-conflict

其他格式: JSON · Markdown 中文 · English
90%修复率
88%置信度
1证据数
2023-07-01首次发现

版本兼容性

版本状态引入弃用备注
transformers>=4.25.0 active — — —

根因分析

在生成配置或 model.generate() 中同时设置了 repetition_penalty 和 no_repeat_ngram_size，但它们可能对 token 选择产生矛盾的效果。

English

Both repetition_penalty and no_repeat_ngram_size are set in generation config or passed to model.generate(), but they can produce contradictory effects on token selection.

generic

官方文档

https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.GenerationConfig

解决方案

  1. Remove one of the parameters: use only `repetition_penalty=1.2` (typical range 1.0-2.0) to discourage repetition, or `no_repeat_ngram_size=3` to block n-gram repeats. Example: `model.generate(inputs, repetition_penalty=1.2)` or `model.generate(inputs, no_repeat_ngram_size=3)`
  2. If you need both effects, implement a custom repetition penalty that combines both strategies manually in a logits processor, then pass it via `model.generate(logits_processor=[...])`.
  3. Check the generation config before calling: `if hasattr(model.generation_config, 'repetition_penalty') and model.generation_config.repetition_penalty is not None: model.generation_config.no_repeat_ngram_size = None`

无效尝试

常见但无效的做法:

  1. 60% 失败

    Setting no_repeat_ngram_size=0 is valid but still triggers the conflict check; setting repetition_penalty=0.0 is invalid (must be >=1.0) and raises a different error.

  2. 50% 失败

    The error is raised before generation; silent catch will cause the generation to proceed with default values, potentially producing unwanted repetition.

  3. 70% 失败

    The GenerationConfig itself raises this error during validation, so it will fail before any generation occurs.