Buckets:
| # -*- coding: utf-8 -*- | |
| from __future__ import annotations | |
| from abc import ABC, abstractmethod | |
| from typing import Dict, Any, Optional, Sequence | |
| import numpy as np | |
| import torch | |
| class RecommenderBase(ABC, torch.nn.Module): | |
| def export_agent_embeddings(self) -> np.ndarray: | |
| """Return agent embedding matrix A: (Na, F) as numpy float32.""" | |
| raise NotImplementedError | |
| def export_query_embeddings(self, q_indices: Sequence[int]) -> np.ndarray: | |
| """Return query embeddings for given q_indices: (Nq, F) as numpy float32.""" | |
| raise NotImplementedError | |
| def export_agent_bias(self) -> Optional[np.ndarray]: | |
| """Return agent bias: (Na,) float32 or None.""" | |
| raise NotImplementedError | |
| def extra_state_dict(self) -> Dict[str, Any]: | |
| """Any extra metadata to checkpoint.""" | |
| raise NotImplementedError | |
Xet Storage Details
- Size:
- 944 Bytes
- Xet hash:
- ab162354bb8066bdcfbaa78a018784d084e8dee5e283ba0a344edadad15e16c5
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.