Skip to content

Commit 87f7f76

Browse files
authored
support Qwen2.5-Omni-3B (#4052)
1 parent 769267f commit 87f7f76

File tree

3 files changed

+3
-0
lines changed

3 files changed

+3
-0
lines changed

docs/source/Instruction/支持的模型和数据集.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -573,6 +573,7 @@
573573
|[Qwen/Qwen2.5-VL-7B-Instruct-AWQ](https://modelscope.cn/models/Qwen/Qwen2.5-VL-7B-Instruct-AWQ)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|✘|vision, video|[Qwen/Qwen2.5-VL-7B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct-AWQ)|
574574
|[Qwen/Qwen2.5-VL-32B-Instruct-AWQ](https://modelscope.cn/models/Qwen/Qwen2.5-VL-32B-Instruct-AWQ)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|✘|vision, video|[Qwen/Qwen2.5-VL-32B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct-AWQ)|
575575
|[Qwen/Qwen2.5-VL-72B-Instruct-AWQ](https://modelscope.cn/models/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|✘|vision, video|[Qwen/Qwen2.5-VL-72B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)|
576+
|[Qwen/Qwen2.5-Omni-3B](https://modelscope.cn/models/Qwen/Qwen2.5-Omni-3B)|qwen2_5_omni|qwen2_5_omni|transformers>=4.50, soundfile, qwen_omni_utils, decord|✘|vision, video, audio|[Qwen/Qwen2.5-Omni-3B](https://huggingface.co/Qwen/Qwen2.5-Omni-3B)|
576577
|[Qwen/Qwen2.5-Omni-7B](https://modelscope.cn/models/Qwen/Qwen2.5-Omni-7B)|qwen2_5_omni|qwen2_5_omni|transformers>=4.50, soundfile, qwen_omni_utils, decord|✘|vision, video, audio|[Qwen/Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B)|
577578
|[Qwen/Qwen2-Audio-7B-Instruct](https://modelscope.cn/models/Qwen/Qwen2-Audio-7B-Instruct)|qwen2_audio|qwen2_audio|transformers>=4.45,<4.49, librosa|&#x2718;|audio|[Qwen/Qwen2-Audio-7B-Instruct](https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct)|
578579
|[Qwen/Qwen2-Audio-7B](https://modelscope.cn/models/Qwen/Qwen2-Audio-7B)|qwen2_audio|qwen2_audio|transformers>=4.45,<4.49, librosa|&#x2718;|audio|[Qwen/Qwen2-Audio-7B](https://huggingface.co/Qwen/Qwen2-Audio-7B)|

docs/source_en/Instruction/Supported-models-and-datasets.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -573,6 +573,7 @@ The table below introduces the models integrated with ms-swift:
573573
|[Qwen/Qwen2.5-VL-7B-Instruct-AWQ](https://modelscope.cn/models/Qwen/Qwen2.5-VL-7B-Instruct-AWQ)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|&#x2718;|vision, video|[Qwen/Qwen2.5-VL-7B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct-AWQ)|
574574
|[Qwen/Qwen2.5-VL-32B-Instruct-AWQ](https://modelscope.cn/models/Qwen/Qwen2.5-VL-32B-Instruct-AWQ)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|&#x2718;|vision, video|[Qwen/Qwen2.5-VL-32B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct-AWQ)|
575575
|[Qwen/Qwen2.5-VL-72B-Instruct-AWQ](https://modelscope.cn/models/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|&#x2718;|vision, video|[Qwen/Qwen2.5-VL-72B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)|
576+
|[Qwen/Qwen2.5-Omni-3B](https://modelscope.cn/models/Qwen/Qwen2.5-Omni-3B)|qwen2_5_omni|qwen2_5_omni|transformers>=4.50, soundfile, qwen_omni_utils, decord|&#x2718;|vision, video, audio|[Qwen/Qwen2.5-Omni-3B](https://huggingface.co/Qwen/Qwen2.5-Omni-3B)|
576577
|[Qwen/Qwen2.5-Omni-7B](https://modelscope.cn/models/Qwen/Qwen2.5-Omni-7B)|qwen2_5_omni|qwen2_5_omni|transformers>=4.50, soundfile, qwen_omni_utils, decord|&#x2718;|vision, video, audio|[Qwen/Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B)|
577578
|[Qwen/Qwen2-Audio-7B-Instruct](https://modelscope.cn/models/Qwen/Qwen2-Audio-7B-Instruct)|qwen2_audio|qwen2_audio|transformers>=4.45,<4.49, librosa|&#x2718;|audio|[Qwen/Qwen2-Audio-7B-Instruct](https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct)|
578579
|[Qwen/Qwen2-Audio-7B](https://modelscope.cn/models/Qwen/Qwen2-Audio-7B)|qwen2_audio|qwen2_audio|transformers>=4.45,<4.49, librosa|&#x2718;|audio|[Qwen/Qwen2-Audio-7B](https://huggingface.co/Qwen/Qwen2-Audio-7B)|

swift/llm/model/model/qwen.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -679,6 +679,7 @@ def get_model_tokenizer_qwen2_5_omni(model_dir, *args, **kwargs):
679679
MLLMModelType.qwen2_5_omni,
680680
[
681681
ModelGroup([
682+
Model('Qwen/Qwen2.5-Omni-3B', 'Qwen/Qwen2.5-Omni-3B'),
682683
Model('Qwen/Qwen2.5-Omni-7B', 'Qwen/Qwen2.5-Omni-7B'),
683684
]),
684685
],

0 commit comments

Comments
 (0)