def __init__(self, path: str ,device: str = 'cpu'):
""" Init the NER Albert """
if not os.path.exists(path):
raise NotADirectoryError(
f"{os.path.abspath(path)} must be a directory containing the model files: config, tokenizer, weights.")
files = os.listdir(path)
if CONFIG_JSON_FILE not in files:
raise FileNotFoundError(f"{CONFIG_JSON_FILE} must be in {path}.")
if WEIGHTS_FILE not in files:
raise FileNotFoundError(f"{WEIGHTS_FILE} must be in {path}.")
with open(os.path.join(path, CONFIG_JSON_FILE), "r") as f:
config = json.load(f)
self.tokenizer = AutoTokenizer.from_pretrained(path)
weights = torch.load(os.path.join(path, WEIGHTS_FILE),
map_location=lambda storage, loc: storage)
# Load pretrained model/tokenizer
config = AlbertConfig.from_dict(config)
self.model = AlbertForTokenClassification(config)
self.model.load_state_dict(weights)
self.model = self.model.eval()
self.args = albert_args_ner
if device == "cuda":
logger.debug("Setting model with CUDA")
self.args['device'] = 'cuda'
self.model.to('cuda')
"attention_probs_dropout_prob": 0,
"bos_token_id": 2,
"classifier_dropout_prob": 0.1,
"embedding_size": 128,
"eos_token_id": 3,
"hidden_act": "gelu_new",
"hidden_dropout_prob": 0,
"hidden_size": 4096,
"initializer_range": 0.02,
"inner_group_num": 1,
"intermediate_size": 16384,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "albert",
"num_attention_heads": 64,
"num_hidden_groups": 1,
"num_hidden_layers": 12,
"pad_token_id": 0,
"type_vocab_size": 2,
"vocab_size": 30000
}
for parameter in albert_config.keys():
albert_config[parameter] = config_dict[parameter]
albert_config = AlbertConfig.from_dict(albert_config)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
stream_handler = logging.StreamHandler()
logger.addHandler(stream_handler)
init_process(0, "gloo", config, albert_config, logger)
