Views
No views yet
per_device_train_batch_size = 48
n_epochs = 1
vocab_size = 52.000
max_position_embeddings = 514
num_attention_heads = 12
num_hidden_layers = 6
type_vocab_size = 1
learning_rate=0.000051from transformers import (
2 pipeline,
3 AutoTokenizer,
4 AutoModelWithLMHead
5)
6
7model_name = "neurocode/IsRoBERTa"
8
9tokenizer = AutoTokenizer.from_pretrained(model_name)
10model = AutoModelWithLMHead.from_pretrained(model_name)
11>>> fill_mask = pipeline(
12... "fill-mask",
13... model=model,
14... tokenizer=tokenizer
15... )
16>>> result = fill_mask("Hann fór út að <mask>.")
17>>> result
18[
19 {'sequence': '<s>Hann fór út að nýju.</s>', 'score': 0.03395755589008331, 'token': 2219, 'token_str': 'Ġnýju'},
20 {'sequence': '<s>Hann fór út að undanförnu.</s>', 'score': 0.029087543487548828, 'token': 7590, 'token_str': 'Ġundanförnu'},
21 {'sequence': '<s>Hann fór út að lokum.</s>', 'score': 0.024420788511633873, 'token': 4384, 'token_str': 'Ġlokum'},
22 {'sequence': '<s>Hann fór út að þessu.</s>', 'score': 0.021231256425380707, 'token': 921, 'token_str': 'Ġþessu'},
23 {'sequence': '<s>Hann fór út að honum.</s>', 'score': 0.0205782949924469, 'token': 1136, 'token_str': 'Ġhonum'}
24]contact [at] donchev.is
Elena Cramer: elena.cramer [at] neurocode.io