import onnxruntime_genai as og

# Load the model

model = og.Model("haydso/tiny-GptOssForCausalLM-ONNX")

tokenizer = og.Tokenizer(model)

# Generate text

prompt = "Your prompt here"

tokens = tokenizer.encode(prompt)

params = og.GeneratorParams(model)

params.set_search_options(max_length=200)

params.input_ids = tokens

generator = og.Generator(model, params)

while not generator.is_done():

    generator.compute_logits()

    generator.generate_next_token()

output_tokens = generator.get_sequence(0)

text = tokenizer.decode(output_tokens)

print(text)

Original Model Card

Tiny GptOssForCausalLM

This is a minimal model built for unit tests in the TRL library.