train_file=train_file,
val_file=val_file,
)
# In[ ]:
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# In[ ]:
T = TypeVar("T")
TensorDict = Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]]
# In[ ]:
processor = BertPreprocessor(config.model_type, config.max_seq_len)
# In[ ]:
DATA_ROOT = Path("../data")
MODEL_SAVE_DIR = Path("../weights")
# Read the model in here
# In[ ]:
from pytorch_pretrained_bert import BertConfig, BertForMaskedLM
masked_lm = BertForMaskedLM.from_pretrained(config.model_type)
masked_lm.eval()
# In[ ]:
sys.path.append("../lib")
# In[4]:
from bert_utils import Config, BertPreprocessor
# In[5]:
config = Config(
model_type="bert-base-uncased",
max_seq_len=128,
)
# In[6]:
processor = BertPreprocessor(config.model_type, config.max_seq_len)
# In[ ]:
# In[7]:
from pytorch_pretrained_bert import BertConfig, BertForMaskedLM
model = BertForMaskedLM.from_pretrained(config.model_type)
model.eval() # Important! Disable dropout
# In[8]:
def get_logits(sentence: str) -> np.ndarray:
return model(processor.to_bert_model_input(sentence))[
0, :, :].cpu().detach().numpy()
sys.path.append("../lib")
# In[4]:
from bert_utils import Config, BertPreprocessor
# In[5]:
config = Config(
model_type="bert-base-uncased",
max_seq_len=128,
)
# In[6]:
processor = BertPreprocessor(config.model_type, config.max_seq_len)
# ### Prepare model
# In[7]:
from pytorch_pretrained_bert import BertConfig, BertForMaskedLM
model = BertForMaskedLM.from_pretrained(config.model_type)
model.eval()
# In[8]:
sequence_output, pooled_output = model.bert(
processor.to_bert_model_input("hello world"),
output_all_encoded_layers=False)