metadata
license: apache-2.0
datasets:
- wikimedia/wikipedia
language:
- id
base_model:
- openai-community/gpt2
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import TextStreamer
model_name = "akahana/wikipedia-gpt2"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
wikipedia_prompt = """Artikel Wikipedia
[[Judul]]
{}
[[Artikel]]
{}"""
title = "Hal Holbrook"
prompt = wikipedia_prompt.format(title, "")
model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512,
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
response