roneneldan/TinyStories-3M

Model trained on the TinyStories Dataset, see https://arxiv.org/abs/2305.07759

------ EXAMPLE USAGE ---

from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig

model = AutoModelForCausalLM.from_pretrained('roneneldan/TinyStories-3M')

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")

prompt = "Once upon a time there was"

inputids = tokenizer.encode(prompt, returntensors="pt")

Generate completion

output = model.generate(inputids, maxlength = 1000, num_beams=1)

Decode the completion

outputtext = tokenizer.decode(output[0], skipspecial_tokens=True)

Print the generated text

print(output_text)