# ValueError: `early_stopping` 设置为 True，但 `num_beams` 为 1。没有 beam search 时，early stopping 无效。

- **ID:** `huggingface/generation-early-stopping-conflict`
- **领域:** huggingface
- **类别:** config_error
- **验证级别:** ai_generated
- **修复率:** 95%

## 根因

Hugging Face 的 `generate()` 方法中的 `early_stopping` 参数仅在 beam search（num_beams > 1）时生效。在贪心或多模态采样中设置它无效，会引发 ValueError 以防止静默配置错误。

## 版本兼容性

| 版本 | 状态 | 引入 | 弃用 |
|------|------|------|------|
| transformers>=4.28.0 | active | — | — |
| torch>=1.12.0 | active | — | — |

## 解决方案

1. ```
   Set `num_beams` to a value greater than 1 to enable beam search and make `early_stopping` effective. For example: `model.generate(input_ids, num_beams=4, early_stopping=True)`.
   ```
2. ```
   Remove `early_stopping` from the generation config if greedy decoding is intended. Use `do_sample=False` (default) instead.
   ```

## 无效尝试

- **** — Setting `num_beams=1` and `early_stopping=False` silences the error but removes the benefit of early stopping when beam search is intended. (30% 失败率)
- **** — Setting `early_stopping='never'` (a string value) is deprecated and may cause a different error in newer versions. (60% 失败率)