Files
wehub-resource-sync e06fe8e8c6
Secret Leaks / trufflehog (push) Failing after 1s
Build documentation / build (push) Failing after 1s
Build documentation / build_other_lang (push) Failing after 0s
CodeQL Security Analysis / CodeQL Analysis (push) Failing after 0s
PR CI / pr-ci (push) Failing after 1s
Slow tests on important models (on Push - A10) / Get all modified files (push) Failing after 1s
Slow tests on important models (on Push - A10) / Model CI (push) Has been skipped
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 11:57:37 +08:00

45 lines
2.7 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Copyright 2025 HuggingFace Inc.
#
# 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 DeepseekVLProcessor
from transformers.testing_utils import get_tests_dir
from ...test_processing_common import ProcessorTesterMixin
SAMPLE_VOCAB = get_tests_dir("fixtures/test_sentencepiece.model")
class DeepseekVLProcessorTest(ProcessorTesterMixin, unittest.TestCase):
processor_class = DeepseekVLProcessor
@classmethod
def _setup_tokenizer(cls):
tokenizer_class = cls._get_component_class_from_processor("tokenizer")
return tokenizer_class.from_pretrained(
SAMPLE_VOCAB,
extra_special_tokens={
"pad_token": "<end▁of▁sentence>",
"image_token": "<image_placeholder>",
},
)
@staticmethod
def prepare_processor_dict():
return {
"chat_template": "{% set seps = ['\n\n', '<\uff5cend\u2581of\u2581sentence\uff5c>'] %}{% set i = 0 %}You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.\n\n{% for message in messages %}{% if message['role']|lower == 'user' %}User: {% elif message['role']|lower == 'assistant' %}Assistant:{% if not (loop.last and not add_generation_prompt and message['content'][0]['type']=='text' and message['content'][0]['text']=='') %} {% endif %}{% else %}{{ message['role'].capitalize() }}: {% endif %}{% for content in message['content'] %}{% if content['type'] == 'image' %}<image_placeholder>{% elif content['type'] == 'text' %}{% set text = content['text'] %}{% if loop.first %}{% set text = text.lstrip() %}{% endif %}{% if loop.last %}{% set text = text.rstrip() %}{% endif %}{% if not loop.first and message['content'][loop.index0-1]['type'] == 'text' %}{{ ' ' + text }}{% else %}{{ text }}{% endif %}{% endif %}{% endfor %}{% if not loop.last or add_generation_prompt %}{% if message['role']|lower == 'user' %}{{ seps[0] }}{% else %}{{ seps[1] }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}Assistant:{% endif %}",
"num_image_tokens": 4,
} # fmt: skip