SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Reorganize repo (#8580)

Browse Source 
* Put models in subfolders

* Styling

* Fix imports in tests

* More fixes in test imports

* Sneaky hidden imports

* Fix imports in doc files

* More sneaky imports

* Finish fixing tests

* Fix examples

* Fix path for copies

* More fixes for examples

* Fix dummy files

* More fixes for example

* More model import fixes

* Is this why you're unhappy GitHub?

* Fix imports in conver command
This commit is contained in:
Sylvain Gugger
2020-11-16 21:43:42 -05:00
committed by GitHub
parent 901507335f
commit c89bdfbe72
381 changed files with 2651 additions and 1571 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/rag/distributed_retriever.py
View File

@@ -27,7 +27,7 @@ class RagPyTorchDistributedRetriever(RagRetriever):
It is used to decode the question and then use the generator_tokenizer.
generator_tokenizer (:class:`~transformers.PretrainedTokenizer`):
The tokenizer used for the generator part of the RagModel.
index (:class:`~transformers.retrieval_rag.Index`, optional, defaults to the one defined by the configuration):
index (:class:`~transformers.models.rag.retrieval_rag.Index`, optional, defaults to the one defined by the configuration):
If specified, use this index instead of the one built using the configuration
"""

14
examples/rag/test_distributed_retriever.py
View File

@@ -11,16 +11,12 @@ import numpy as np
from datasets import Dataset
import faiss
from transformers.configuration_bart import BartConfig
from transformers.configuration_dpr import DPRConfig
from transformers.configuration_rag import RagConfig
from transformers import BartConfig, BartTokenizer, DPRConfig, DPRQuestionEncoderTokenizer, RagConfig
from transformers.file_utils import is_datasets_available, is_faiss_available, is_psutil_available, is_torch_available
from transformers.retrieval_rag import CustomHFIndex
from transformers.models.bert.tokenization_bert import VOCAB_FILES_NAMES as DPR_VOCAB_FILES_NAMES
from transformers.models.rag.retrieval_rag import CustomHFIndex
from transformers.models.roberta.tokenization_roberta import VOCAB_FILES_NAMES as BART_VOCAB_FILES_NAMES
from transformers.testing_utils import require_torch_non_multi_gpu_but_fix_me
from transformers.tokenization_bart import BartTokenizer
from transformers.tokenization_bert import VOCAB_FILES_NAMES as DPR_VOCAB_FILES_NAMES
from transformers.tokenization_dpr import DPRQuestionEncoderTokenizer
from transformers.tokenization_roberta import VOCAB_FILES_NAMES as BART_VOCAB_FILES_NAMES
sys.path.append(os.path.join(os.getcwd())) # noqa: E402 # noqa: E402 # isort:skip
@@ -137,7 +133,7 @@ class RagRetrieverTest(TestCase):
question_encoder=DPRConfig().to_dict(),
generator=BartConfig().to_dict(),
)
with patch("transformers.retrieval_rag.load_dataset") as mock_load_dataset:
with patch("transformers.models.rag.retrieval_rag.load_dataset") as mock_load_dataset:
mock_load_dataset.return_value = dataset
retriever = RagPyTorchDistributedRetriever(
config,