test_processor_llava.py 1.79 KB
Newer Older
Arthur's avatar
Arthur committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
# Copyright 2021 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.testing_utils import require_vision
from transformers.utils import is_vision_available


if is_vision_available():
    from transformers import AutoTokenizer, LlavaProcessor


@require_vision
class LlavaProcessorTest(unittest.TestCase):
    def test_can_load_various_tokenizers(self):
        for checkpoint in ["Intel/llava-gemma-2b", "llava-hf/llava-1.5-7b-hf"]:
            processor = LlavaProcessor.from_pretrained(checkpoint)
            tokenizer = AutoTokenizer.from_pretrained(checkpoint)
            self.assertEqual(processor.tokenizer.__class__, tokenizer.__class__)
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47

    def test_chat_template(self):
        processor = LlavaProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf")
        expected_prompt = "USER: <image>\nWhat is shown in this image? ASSISTANT:"

        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.assertEquals(expected_prompt, formatted_prompt)