Perform Fill-in-the-Blank Tasks

Tries to fill in a hole with a missing word (token to be precise). That’s the base task for BERT models.

Usage

hf_ez_fill_mask(model_id = "google-bert/bert-base-uncased", use_api = FALSE)

Arguments

model_id

A model_id. Run hf_search_models(...) for model_ids. Defaults to 'bert-base-uncased'.

use_api

Whether to use the Inference API to run the model (TRUE) or download and run the model locally (FALSE). Defaults to FALSE

Value

A fill mask object

See also

https://huggingface.co/docs/api-inference/detailed_parameters#fill-mask-task

Examples

if (FALSE) { # \dontrun{
# Load the default model and use local inference
ez <- hf_ez_fill_mask()
ez$infer(string = "The answer to the universe is [MASK].")

# Load a specific model and use the api for inference. Note the mask is different for different models.
ez <- hf_ez_fill_mask(model_id = 'xlm-roberta-base', use_api = TRUE)
ez$infer(string = "The answer to the universe is <MASK>.")
} # }