hf_load_pipeline: Load a pipeline object from Hugging Face - pipelines usually...

In huggingfaceR: Access 'Hugging Face' Models and Datasets

Load a pipeline object from Hugging Face - pipelines usually include a model, tokenizer and task.

Description

Load Model from Hugging Face

Usage

hf_load_pipeline(model_id, tokenizer = NULL, task = NULL, ...)

Arguments

model_id	The id of the model given in the url by https://huggingface.co/model_name.
tokenizer	The tokenizer function used to tokenize inputs. Defaults to NULL (one will be automatically loaded).
task	The task the model will accomplish. Run hf_list_tasks() for options.
...	Fed to the hf_pipeline function

Value

A Hugging Face model ready for prediction.

See Also

https://huggingface.co/docs/transformers/main/en/pipeline_tutorial

Examples

## Not run: 
pipe <- hf_load_pipeline("distilbert-base-uncased-finetuned-sst-2-english",
                         task = "sentiment-analysis")
pipe("I love R.")

## End(Not run)

huggingfaceR documentation built on Aug. 30, 2026, 1:06 a.m.