def openAIGPTModel(*args, **kwargs):
"""
OpenAIGPTModel is the basic OpenAI GPT Transformer model based on
identical stacked masked self-attention blocks and pre-trained
on large scale dataset using language modeling signal.
Example:
# Load the tokenizer
>>> import torch
>>> tokenizer = torch.hub.load('huggingface/pytorch-transformers', 'openAIGPTTokenizer', 'openai-gpt')
# Prepare tokenized input
>>> text = "Who was Jim Henson ? Jim Henson was a puppeteer"
>>> tokenized_text = tokenizer.tokenize(text)
>>> indexed_tokens = tokenizer.convert_tokens_to_ids(tokenized_text)
>>> tokens_tensor = torch.tensor([indexed_tokens])
# Load openAIGPTModel
>>> model = torch.hub.load('huggingface/pytorch-transformers', 'openAIGPTModel', 'openai-gpt')
>>> model.eval()
# Predict hidden states features for each layer
>>> with torch.no_grad():
hidden_states = model(tokens_tensor)
"""
model = OpenAIGPTModel.from_pretrained(*args, **kwargs)
return model
def convert_openai_checkpoint_to_pytorch(openai_checkpoint_folder_path,
openai_config_file,
pytorch_dump_folder_path):
# Construct model
if openai_config_file == "":
config = OpenAIGPTConfig()
else:
config = OpenAIGPTConfig.from_json_file(openai_config_file)
model = OpenAIGPTModel(config)
# Load weights from numpy
load_tf_weights_in_openai_gpt(model, config, openai_checkpoint_folder_path)
# Save pytorch-model
pytorch_weights_dump_path = pytorch_dump_folder_path + '/' + WEIGHTS_NAME
pytorch_config_dump_path = pytorch_dump_folder_path + '/' + CONFIG_NAME
print("Save PyTorch model to {}".format(pytorch_weights_dump_path))
torch.save(model.state_dict(), pytorch_weights_dump_path)
print("Save configuration file to {}".format(pytorch_config_dump_path))
with open(pytorch_config_dump_path, "w", encoding="utf-8") as f:
f.write(config.to_json_string())