sherrytonger

I deduce gandiva does not support overflow check from the following pic. Will it support that in the future? Besides, does somebody know how to detect overflow using LLVM api...

为什么大部分的refined recipe都是用simhash去重？

1

### Before Asking 在提问之前 - [X] I have read the [README](https://github.com/alibaba/data-juicer/blob/main/README.md) carefully. 我已经仔细阅读了 [README](https://github.com/alibaba/data-juicer/blob/main/README_ZH.md) 上的操作指引。 - [X] I have pulled the latest code of main branch to run again and...

when execute the following code: ```python quantized_model = IPEXModel.from_pretrained(self.model_path).eval() model_ref = ray.put(quantized_model ) ``` Error message: ``` RuntimeError: Tried to serialize object __torch__.intel_extension_for_pytorch.quantization._quantize_utils.___torch_mangle_972.QuantizationDispatchModule which does not have a __getstate__ method...