mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 13:20:12 +06:00
be236361f1
* Tentative enabling of `batch_size` for pipelines. * Add systematic test for pipeline batching. * Enabling batch_size on almost all pipelines - Not `zero-shot` (it's already passing stuff as batched so trickier) - Not `QA` (preprocess uses squad features, we need to switch to real tensors at this boundary. * Adding `min_length_for_response` for conversational. * Making CTC, speech mappings avaiable regardless of framework. * Attempt at fixing automatic tests (ffmpeg not enabled for fast tests) * Removing ffmpeg dependency in tests. * Small fixes. * Slight cleanup. * Adding docs and adressing comments. * Quality. * Update docs/source/main_classes/pipelines.rst Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/pipelines/question_answering.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/pipelines/zero_shot_classification.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Improving docs. * Update docs/source/main_classes/pipelines.rst Co-authored-by: Philipp Schmid <32632186+philschmid@users.noreply.github.com> * N -> oberved_batch_size softmax trick. * Follow `padding_side`. * Supporting image pipeline batching (and padding). * Rename `unbatch` -> `loader_batch`. * unbatch_size forgot. * Custom padding for offset mappings. * Attempt to remove librosa. * Adding require_audio. * torchaudio. * Back to using datasets librosa. * Adding help to set a pad_token on the tokenizer. * Update src/transformers/pipelines/base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/pipelines/base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/pipelines/base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Quality. Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Philipp Schmid <32632186+philschmid@users.noreply.github.com>
59 lines
2.4 KiB
Python
59 lines
2.4 KiB
Python
# Copyright 2020 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import unittest
|
|
|
|
from transformers import (
|
|
MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING,
|
|
TF_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING,
|
|
Text2TextGenerationPipeline,
|
|
pipeline,
|
|
)
|
|
from transformers.testing_utils import is_pipeline_test, require_tf, require_torch
|
|
|
|
from .test_pipelines_common import ANY, PipelineTestCaseMeta
|
|
|
|
|
|
@is_pipeline_test
|
|
class Text2TextGenerationPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
|
|
model_mapping = MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING
|
|
tf_model_mapping = TF_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING
|
|
|
|
def get_test_pipeline(self, model, tokenizer, feature_extractor):
|
|
generator = Text2TextGenerationPipeline(model=model, tokenizer=tokenizer)
|
|
return generator, ["Something to write", "Something else"]
|
|
|
|
def run_pipeline_test(self, generator, _):
|
|
outputs = generator("Something there")
|
|
self.assertEqual(outputs, [{"generated_text": ANY(str)}])
|
|
# These are encoder decoder, they don't just append to incoming string
|
|
self.assertFalse(outputs[0]["generated_text"].startswith("Something there"))
|
|
|
|
with self.assertRaises(ValueError):
|
|
generator(4)
|
|
|
|
@require_torch
|
|
def test_small_model_pt(self):
|
|
generator = pipeline("text2text-generation", model="patrickvonplaten/t5-tiny-random", framework="pt")
|
|
# do_sample=False necessary for reproducibility
|
|
outputs = generator("Something there", do_sample=False)
|
|
self.assertEqual(outputs, [{"generated_text": ""}])
|
|
|
|
@require_tf
|
|
def test_small_model_tf(self):
|
|
generator = pipeline("text2text-generation", model="patrickvonplaten/t5-tiny-random", framework="tf")
|
|
# do_sample=False necessary for reproducibility
|
|
outputs = generator("Something there", do_sample=False)
|
|
self.assertEqual(outputs, [{"generated_text": ""}])
|