model_utils#
- class FasterPretrainedModel(*args, **kwargs)[源代码]#
- to_static(output_path)[源代码]#
export generation model to static
- 参数:
path (str) -- path of saved inference model
config (dict) -- configuration for generation bos_token_id (int): token id of begin-of-sentence eos_token_id (int): token id of end-of-sentence pad_token_id (int): token id of pad token use_top_p (bool): whether use top_p decoding strategy
- classmethod from_pretrained(pretrained_model_name_or_path, *args, **kwargs)[源代码]#
Creates an instance of
PretrainedModel
. Model weights are loaded by specifying name of a built-in pretrained model, or a community contributed model, or a local file directory path.- 参数:
pretrained_model_name_or_path (str) --
Name of pretrained model or dir path to load from. The string can be:
Name of a built-in pretrained model
Name of a community-contributed pretrained model.
Local directory path which contains model weights file("model_state.pdparams") and model config file ("model_config.json").
*args (tuple) -- Position arguments for model
__init__
. If provided, use these as position argument values for model initialization.**kwargs (dict) -- Keyword arguments for model
__init__
. If provided, use these to update pre-defined keyword argument values for model initialization. If the keyword is in__init__
argument names of base model, update argument values of the base model; else update argument values of derived model.
- 返回:
An instance of
PretrainedModel
.- 返回类型:
示例
from paddlenlp.transformers import BertForSequenceClassification # Name of built-in pretrained model model = BertForSequenceClassification.from_pretrained('bert-base-uncased') # Name of community-contributed pretrained model model = BertForSequenceClassification.from_pretrained('yingyibiao/bert-base-uncased-sst-2-finetuned') # Load from local directory path model = BertForSequenceClassification.from_pretrained('./my_bert/')
- save_pretrained(save_dir)[源代码]#
Saves model configuration and related resources (model state) as files under
save_dir
. The model configuration would be saved into a file named "model_config.json", and model state would be saved into a file named "model_state.pdparams".The
save_dir
can be used infrom_pretrained
as argument value ofpretrained_model_name_or_path
to re-load the trained model.- 参数:
save_dir (str) -- Directory to save files into.
示例
from paddlenlp.transformers import BertForSequenceClassification model = BertForSequenceClassification.from_pretrained('bert-base-uncased') model.save_pretrained('./trained_model/') # reload from save_directory model = BertForSequenceClassification.from_pretrained('./trained_model/')