mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-08 07:10:06 +06:00
86822a358b
* add mt5 and t5v1_1 model * fix tests * correct some imports * add tf model * finish tf t5 * improve examples * fix copies * clean doc
40 lines
1.6 KiB
Python
40 lines
1.6 KiB
Python
import unittest
|
|
|
|
from transformers import is_torch_available
|
|
from transformers.testing_utils import require_sentencepiece, require_tokenizers, require_torch, slow, torch_device
|
|
|
|
|
|
if is_torch_available():
|
|
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
|
|
|
|
|
@require_torch
|
|
@require_sentencepiece
|
|
@require_tokenizers
|
|
class MT5IntegrationTest(unittest.TestCase):
|
|
@slow
|
|
def test_small_integration_test(self):
|
|
"""
|
|
For comparision run:
|
|
>>> import t5 # pip install t5==0.7.1
|
|
>>> from t5.data.sentencepiece_vocabulary import SentencePieceVocabulary
|
|
|
|
>>> path_to_mtf_small_mt5_checkpoint = '<fill_in>'
|
|
>>> path_to_mtf_small_mt5_spm_model_path = '<fill_in>'
|
|
>>> t5_model = t5.models.MtfModel(model_dir=path_to_mtf_small_mt5_checkpoint, batch_size=1, tpu=None)
|
|
>>> vocab = SentencePieceVocabulary(path_to_mtf_small_mt5_spm_model_path)
|
|
>>> score = t5_model.score(inputs=["Hello there"], targets=["Hi I am"], vocabulary=vocab)
|
|
"""
|
|
|
|
model = AutoModelForSeq2SeqLM.from_pretrained("google/mt5-small", return_dict=True).to(torch_device)
|
|
tokenizer = AutoTokenizer.from_pretrained("google/mt5-small")
|
|
|
|
input_ids = tokenizer("Hello there", return_tensors="pt").input_ids
|
|
labels = tokenizer("Hi I am", return_tensors="pt").input_ids
|
|
|
|
loss = model(input_ids.to(torch_device), labels=labels.to(torch_device)).loss
|
|
mtf_score = -(labels.shape[-1] * loss.item())
|
|
|
|
EXPECTED_SCORE = -84.9127
|
|
self.assertTrue(abs(mtf_score - EXPECTED_SCORE) < 1e-4)
|