FMAT_load: [Deprecated] Load BERT models (useless for GPU).

View source: R/FMAT.R

FMAT_loadR Documentation

[Deprecated] Load BERT models (useless for GPU).

Description

Load BERT models from local cache folder "%USERPROFILE%/.cache/huggingface". For GPU Acceleration, please directly use FMAT_run. In general, FMAT_run is always preferred than FMAT_load.

Usage

FMAT_load(models)

Arguments

models

Model names at HuggingFace.

Value

A named list of fill-mask pipelines obtained from the models. The returned object cannot be saved as any RData. You will need to rerun this function if you restart the R session.

See Also

BERT_download

FMAT_query

FMAT_query_bind

FMAT_run

Examples

## Not run: 
models = c("bert-base-uncased", "bert-base-cased")
models = FMAT_load(models)  # load models from cache

## End(Not run)


FMAT documentation built on Sept. 11, 2024, 8:28 p.m.