Skip to main content

GPT-2 implemented in PyTorch

Project description

PyTorch GPT-2

Travis Coverage


pip install torch-gpt-2


import os
import sys
from torch_gpt_2 import load_trained_model_from_checkpoint, get_bpe_from_files, generate

if len(sys.argv) != 2:
    print('python3 MODEL_FOLDER')

model_folder = sys.argv[1]
config_path = os.path.join(model_folder, 'hparams.json')
checkpoint_path = os.path.join(model_folder, 'model.ckpt')
encoder_path = os.path.join(model_folder, 'encoder.json')
vocab_path = os.path.join(model_folder, 'vocab.bpe')

print('Load net from checkpoint...')
net = load_trained_model_from_checkpoint(config_path, checkpoint_path)
print('Load BPE from files...')
bpe = get_bpe_from_files(encoder_path, vocab_path)
print('Generate text...')
output = generate(net, bpe, ['From the day forth, my arm'], length=20, top_k=1)

# If you are using the 117M model and top_k equals to 1, then the result would be:
# "From the day forth, my arm was broken, and I was in a state of pain. I was in a state of pain,"

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

torch-gpt-2-0.3.0.tar.gz (5.9 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page