Text Generation — hf_generate • huggingfaceR

Generate text from a prompt using a language model via the Inference Providers API.

Usage

hf_generate(
  prompt,
  model = "meta-llama/Llama-3.1-8B-Instruct",
  max_new_tokens = 50,
  temperature = 1,
  top_p = NULL,
  token = NULL,
  endpoint_url = NULL,
  ...
)

Arguments

prompt: Character vector of text prompt(s) to generate from.
model: Character string. Model ID from Hugging Face Hub. Default: "meta-llama/Llama-3.1-8B-Instruct".
max_new_tokens: Integer. Maximum number of tokens to generate. Default: 50.
temperature: Numeric. Sampling temperature (0-2). Default: 1.0.
top_p: Numeric. Nucleus sampling parameter. Default: NULL.
token: Character string or NULL. API token for authentication.
endpoint_url: Character string or NULL. A custom Inference Endpoint URL. The endpoint must support the chat completions format.
...: Additional parameters passed to the model.

Value

A tibble with columns: prompt, generated_text

Examples

if (FALSE) { # \dontrun{
# Simple text generation
hf_generate("Once upon a time in a land far away,")

# With different model
hf_generate("The future of AI is", model = "meta-llama/Llama-3-8B-Instruct:together")
} # }