Generate text completions using HuggingFace's API — create_completion_huggingface • gptstudio

Generate text completions using HuggingFace's API

Usage

create_completion_huggingface(
  prompt,
  history = NULL,
  model = "tiiuae/falcon-7b-instruct",
  token = Sys.getenv("HF_API_KEY"),
  max_new_tokens = 250
)

Arguments

prompt: The prompt for generating completions
history: A list of the previous chat responses
model: The model to use for generating text
token: The API key for accessing HuggingFace's API. By default, the function will try to use the HF_API_KEY environment variable.
max_new_tokens: Maximum number of tokens to generate, defaults to 250

Value

A list with the generated completions and other information returned by the API.

Examples

if (FALSE) {
create_completion_huggingface(
  model = "gpt2",
  prompt = "Hello world!"
)
}