Raphael
Raphael
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc2 in position 2799: ordinal not in range(128)
retriever = DenseRetriever( index_name=self.index_name, model="/data/rfzhang/harmfultext/model/sentence-transformers", normalize=True, max_length=128, use_ann=False, ).index(collection, use_gpu=True) When I run the above code, UnicodeDecodeError appears. I don't understand why it decodes the input in 'ascii'.
After training for a period of time, new episodes cannot be generated.The phenomenon manifested is that training stops. This bug is hard to reproduce because it always appears after a...