Download lam2/lib/python3.8/site-packages/huggingface_hub/serialization/_numpy.py from anusfoil/LLaQo-ckpts: direct link, hf CLI and curl.
- Browser
- Download file 2.69 kB
-
https://huggingface.co/anusfoil/LLaQo-ckpts/resolve/main/lam2/lib/python3.8/site-packages/huggingface_hub/serialization/_numpy.py
- Command line
-
hf download hf://anusfoil/LLaQo-ckpts/lam2/lib/python3.8/site-packages/huggingface_hub/serialization/_numpy.py
-
curl -L -o _numpy.py https://huggingface.co/anusfoil/LLaQo-ckpts/resolve/main/lam2/lib/python3.8/site-packages/huggingface_hub/serialization/_numpy.py
2.69 kB
| # Copyright 2024 The HuggingFace Team. All rights reserved. | |
| # | |
| # Licensed under the Apache License, Version 2.0 (the "License"); | |
| # you may not use this file except in compliance with the License. | |
| # You may obtain a copy of the License at | |
| # | |
| # http://www.apache.org/licenses/LICENSE-2.0 | |
| # | |
| # Unless required by applicable law or agreed to in writing, software | |
| # distributed under the License is distributed on an "AS IS" BASIS, | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| # See the License for the specific language governing permissions and | |
| # limitations under the License. | |
| """Contains numpy-specific helpers.""" | |
| from typing import TYPE_CHECKING, Dict, Union | |
| from ._base import FILENAME_PATTERN, MAX_SHARD_SIZE, StateDictSplit, split_state_dict_into_shards_factory | |
| if TYPE_CHECKING: | |
| import numpy as np | |
| def split_numpy_state_dict_into_shards( | |
| state_dict: Dict[str, "np.ndarray"], | |
| *, | |
| filename_pattern: str = FILENAME_PATTERN, | |
| max_shard_size: Union[int, str] = MAX_SHARD_SIZE, | |
| ) -> StateDictSplit: | |
| """ | |
| Split a model state dictionary in shards so that each shard is smaller than a given size. | |
| The shards are determined by iterating through the `state_dict` in the order of its keys. There is no optimization | |
| made to make each shard as close as possible to the maximum size passed. For example, if the limit is 10GB and we | |
| have tensors of sizes [6GB, 6GB, 2GB, 6GB, 2GB, 2GB] they will get sharded as [6GB], [6+2GB], [6+2+2GB] and not | |
| [6+2+2GB], [6+2GB], [6GB]. | |
| <Tip warning={true}> | |
| If one of the model's tensor is bigger than `max_shard_size`, it will end up in its own shard which will have a | |
| size greater than `max_shard_size`. | |
| </Tip> | |
| Args: | |
| state_dict (`Dict[str, np.ndarray]`): | |
| The state dictionary to save. | |
| filename_pattern (`str`, *optional*): | |
| The pattern to generate the files names in which the model will be saved. Pattern must be a string that | |
| can be formatted with `filename_pattern.format(suffix=...)` and must contain the keyword `suffix` | |
| Defaults to `"model{suffix}.safetensors"`. | |
| max_shard_size (`int` or `str`, *optional*): | |
| The maximum size of each shard, in bytes. Defaults to 5GB. | |
| Returns: | |
| [`StateDictSplit`]: A `StateDictSplit` object containing the shards and the index to retrieve them. | |
| """ | |
| return split_state_dict_into_shards_factory( | |
| state_dict, | |
| max_shard_size=max_shard_size, | |
| filename_pattern=filename_pattern, | |
| get_tensor_size=get_tensor_size, | |
| ) | |
| def get_tensor_size(tensor: "np.ndarray") -> int: | |
| return tensor.nbytes | |