cuda.is_available() else 'cpu') print(device) # 加载保存的模型 model = AutoModel.from_pretrained('/workspace/01_triton/model_save/model_zoo/bge-reranker-base') def make_train_dummy_input(seq_len): org_input_ids = torch.tensor( [[i for i in range(seq_len)]], dtype=torch.int32)...
服务端报错详情，应该是这个：relevance_score=float(similarity_scores[arg]),