Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
102 lines
4.6 KiB
Python
102 lines
4.6 KiB
Python
# Copyright 2025 The HuggingFace Inc. 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 json
|
|
import unittest
|
|
|
|
from transformers.testing_utils import require_av, require_vision
|
|
from transformers.utils import is_vision_available
|
|
|
|
from ...test_processing_common import ProcessorTesterMixin
|
|
|
|
|
|
if is_vision_available():
|
|
from transformers import (
|
|
AutoProcessor,
|
|
Ovis2Processor,
|
|
)
|
|
|
|
|
|
@require_vision
|
|
class Ovis2ProcessorTest(ProcessorTesterMixin, unittest.TestCase):
|
|
processor_class = Ovis2Processor
|
|
|
|
@classmethod
|
|
def _setup_tokenizer(cls):
|
|
tokenizer_class = cls._get_component_class_from_processor("tokenizer")
|
|
return tokenizer_class.from_pretrained("thisisiron/Ovis2-1B-hf")
|
|
|
|
@staticmethod
|
|
def prepare_processor_dict():
|
|
return {
|
|
"chat_template": "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>\n' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>\n'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}",
|
|
} # fmt: skip
|
|
|
|
def test_processor_to_json_string(self):
|
|
processor = self.get_processor()
|
|
obj = json.loads(processor.to_json_string())
|
|
for key, value in self.prepare_processor_dict().items():
|
|
# chat_tempalate are tested as a separate test because they are saved in separate files
|
|
if key != "chat_template":
|
|
self.assertEqual(obj[key], value)
|
|
self.assertEqual(getattr(processor, key, None), value)
|
|
|
|
def test_chat_template_is_saved(self):
|
|
processor_loaded = self.processor_class.from_pretrained(self.tmpdirname)
|
|
processor_dict_loaded = json.loads(processor_loaded.to_json_string())
|
|
# chat templates aren't serialized to json in processors
|
|
self.assertFalse("chat_template" in processor_dict_loaded)
|
|
|
|
# they have to be saved as separate file and loaded back from that file
|
|
# so we check if the same template is loaded
|
|
processor_dict = self.prepare_processor_dict()
|
|
self.assertTrue(processor_loaded.chat_template == processor_dict.get("chat_template", None))
|
|
|
|
def test_chat_template(self):
|
|
processor = AutoProcessor.from_pretrained("thisisiron/Ovis2-1B-hf")
|
|
expected_prompt = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\nWhat is shown in this image?<|im_end|>\n<|im_start|>assistant\n"
|
|
|
|
messages = [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "image"},
|
|
{"type": "text", "text": "What is shown in this image?"},
|
|
],
|
|
},
|
|
]
|
|
|
|
formatted_prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
|
|
self.assertEqual(expected_prompt, formatted_prompt)
|
|
|
|
@require_av
|
|
def test_chat_template_dict(self):
|
|
processor = AutoProcessor.from_pretrained("thisisiron/Ovis2-1B-hf")
|
|
messages = [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "image"},
|
|
{"type": "text", "text": "What is shown in this image?"},
|
|
],
|
|
},
|
|
]
|
|
|
|
formatted_prompt_tokenized = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True)
|
|
expected_output = [[151644, 8948, 198, 2610, 525, 264, 10950, 17847, 13, 151645, 198, 151644, 872, 198, 27, 1805, 397, 3838, 374, 6839, 304, 419, 2168, 30, 151645, 198, 151644, 77091, 198]] # fmt: skip
|
|
self.assertListEqual(expected_output, formatted_prompt_tokenized)
|
|
|
|
out_dict = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True)
|
|
self.assertListEqual(list(out_dict.keys()), ["input_ids", "attention_mask"])
|