huggingface config_error ai_generated true

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

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

ID: huggingface/generation-repetition-penalty-conflict

其他格式: JSON · Markdown 中文 · English
90%修复率
83%置信度
1证据数
2024-02-10首次发现

版本兼容性

版本状态引入弃用备注
transformers>=4.35.0 active — — —

根因分析

在生成配置中同时设置了 `repetition_penalty` 和 `no_repeat_ngram_size`，但它们的组合效果可能对 token 选择产生矛盾约束。

English

Both `repetition_penalty` and `no_repeat_ngram_size` are set in the generation config, but their combined effect can produce contradictory constraints on token selection.

generic

官方文档

https://huggingface.co/docs/transformers/en/generation_strategies#repetition-penalty

解决方案

  1. Remove one of the conflicting parameters: `model.generate(input_ids, repetition_penalty=1.2)  # no no_repeat_ngram_size` or `model.generate(input_ids, no_repeat_ngram_size=3)  # no repetition_penalty`
  2. Set the removed parameter to its default value explicitly: `model.generate(input_ids, repetition_penalty=1.0, no_repeat_ngram_size=0)`
  3. Use a custom generation config that overrides the conflict check: `from transformers import GenerationConfig; config = GenerationConfig.from_pretrained('model-name', repetition_penalty=1.2, no_repeat_ngram_size=3, _from_model_config=True)` but this may cause undefined behavior.

无效尝试

常见但无效的做法:

  1. Setting both parameters to very low values (e.g., 0.1 and 1) 95% 失败

    The conflict check is boolean; any non-default values for both triggers the error, regardless of magnitude.

  2. Ignoring the warning and proceeding with generation 100% 失败

    This is a ValueError, not a warning; it halts execution entirely.

  3. Upgrading transformers to 4.40.0 80% 失败

    The conflict detection was introduced in 4.35.0; newer versions still enforce the rule.