update

Author: Jintao-Huang

docs/source/Instruction/支持的模型和数据集.md

@@ -598,8 +598,6 @@
 |[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)|
 |[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)|
 |[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)|
-|[XiaomiMiMo/MiMo-VL-7B-SFT](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-SFT)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|✘|vision, video|[XiaomiMiMo/MiMo-VL-7B-SFT](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-SFT)|
-|[XiaomiMiMo/MiMo-VL-7B-RL](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-RL)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|✘|vision, video|[XiaomiMiMo/MiMo-VL-7B-RL](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL)|
 |[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)|
 |[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)|
 |[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)|
@@ -617,6 +615,8 @@
 |[AIDC-AI/Ovis2-8B](https://modelscope.cn/models/AIDC-AI/Ovis2-8B)|ovis2|ovis2|transformers>=4.46.2, moviepy<2|&#x2718;|vision|[AIDC-AI/Ovis2-8B](https://huggingface.co/AIDC-AI/Ovis2-8B)|
 |[AIDC-AI/Ovis2-16B](https://modelscope.cn/models/AIDC-AI/Ovis2-16B)|ovis2|ovis2|transformers>=4.46.2, moviepy<2|&#x2718;|vision|[AIDC-AI/Ovis2-16B](https://huggingface.co/AIDC-AI/Ovis2-16B)|
 |[AIDC-AI/Ovis2-34B](https://modelscope.cn/models/AIDC-AI/Ovis2-34B)|ovis2|ovis2|transformers>=4.46.2, moviepy<2|&#x2718;|vision|[AIDC-AI/Ovis2-34B](https://huggingface.co/AIDC-AI/Ovis2-34B)|
+|[XiaomiMiMo/MiMo-VL-7B-SFT](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-SFT)|mimo_vl|mimo_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|&#x2718;|vision, video|[XiaomiMiMo/MiMo-VL-7B-SFT](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-SFT)|
+|[XiaomiMiMo/MiMo-VL-7B-RL](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-RL)|mimo_vl|mimo_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|&#x2718;|vision, video|[XiaomiMiMo/MiMo-VL-7B-RL](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL)|
 |[ZhipuAI/glm-4v-9b](https://modelscope.cn/models/ZhipuAI/glm-4v-9b)|glm4v|glm4v|transformers>=4.42,<4.45|&#x2718;|-|[THUDM/glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b)|
 |[ZhipuAI/cogagent-9b-20241220](https://modelscope.cn/models/ZhipuAI/cogagent-9b-20241220)|glm4v|glm4v|transformers>=4.42|&#x2718;|-|[THUDM/cogagent-9b-20241220](https://huggingface.co/THUDM/cogagent-9b-20241220)|
 |[ZhipuAI/glm-edge-v-2b](https://modelscope.cn/models/ZhipuAI/glm-edge-v-2b)|glm_edge_v|glm_edge_v|transformers>=4.46|&#x2718;|vision|[THUDM/glm-edge-v-2b](https://huggingface.co/THUDM/glm-edge-v-2b)|

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

@@ -598,8 +598,6 @@ The table below introduces the models integrated with ms-swift:
 |[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)|
 |[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)|
 |[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)|
-|[XiaomiMiMo/MiMo-VL-7B-SFT](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-SFT)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|✘|vision, video|[XiaomiMiMo/MiMo-VL-7B-SFT](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-SFT)|
-|[XiaomiMiMo/MiMo-VL-7B-RL](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-RL)|qwen2_5_vl|qwen2_5_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|✘|vision, video|[XiaomiMiMo/MiMo-VL-7B-RL](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL)|
 |[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)|
 |[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)|
 |[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)|
@@ -617,6 +615,8 @@ The table below introduces the models integrated with ms-swift:
 |[AIDC-AI/Ovis2-8B](https://modelscope.cn/models/AIDC-AI/Ovis2-8B)|ovis2|ovis2|transformers>=4.46.2, moviepy<2|&#x2718;|vision|[AIDC-AI/Ovis2-8B](https://huggingface.co/AIDC-AI/Ovis2-8B)|
 |[AIDC-AI/Ovis2-16B](https://modelscope.cn/models/AIDC-AI/Ovis2-16B)|ovis2|ovis2|transformers>=4.46.2, moviepy<2|&#x2718;|vision|[AIDC-AI/Ovis2-16B](https://huggingface.co/AIDC-AI/Ovis2-16B)|
 |[AIDC-AI/Ovis2-34B](https://modelscope.cn/models/AIDC-AI/Ovis2-34B)|ovis2|ovis2|transformers>=4.46.2, moviepy<2|&#x2718;|vision|[AIDC-AI/Ovis2-34B](https://huggingface.co/AIDC-AI/Ovis2-34B)|
+|[XiaomiMiMo/MiMo-VL-7B-SFT](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-SFT)|mimo_vl|mimo_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|&#x2718;|vision, video|[XiaomiMiMo/MiMo-VL-7B-SFT](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-SFT)|
+|[XiaomiMiMo/MiMo-VL-7B-RL](https://modelscope.cn/models/XiaomiMiMo/MiMo-VL-7B-RL)|mimo_vl|mimo_vl|transformers>=4.49, qwen_vl_utils>=0.0.6, decord|&#x2718;|vision, video|[XiaomiMiMo/MiMo-VL-7B-RL](https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL)|
 |[ZhipuAI/glm-4v-9b](https://modelscope.cn/models/ZhipuAI/glm-4v-9b)|glm4v|glm4v|transformers>=4.42,<4.45|&#x2718;|-|[THUDM/glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b)|
 |[ZhipuAI/cogagent-9b-20241220](https://modelscope.cn/models/ZhipuAI/cogagent-9b-20241220)|glm4v|glm4v|transformers>=4.42|&#x2718;|-|[THUDM/cogagent-9b-20241220](https://huggingface.co/THUDM/cogagent-9b-20241220)|
 |[ZhipuAI/glm-edge-v-2b](https://modelscope.cn/models/ZhipuAI/glm-edge-v-2b)|glm_edge_v|glm_edge_v|transformers>=4.46|&#x2718;|vision|[THUDM/glm-edge-v-2b](https://huggingface.co/THUDM/glm-edge-v-2b)|

swift/llm/model/model/qwen.py

@@ -701,7 +701,6 @@ def get_model_tokenizer_qwen2_5_vl(*args, **kwargs):
         tags=['vision', 'video']))
 
 
-
 def get_model_tokenizer_qwen2_5_omni(model_dir, *args, **kwargs):
     from transformers import Qwen2_5OmniForConditionalGeneration, Qwen2_5OmniProcessor, Qwen2_5OmniConfig
     from qwen_omni_utils import vision_process

swift/llm/template/template/qwen.py

@@ -397,8 +397,12 @@ class Qwen2_5VLTemplate(Qwen2VLTemplate):
 
 register_template(QwenTemplateMeta(MLLMTemplateType.qwen2_5_vl, template_cls=Qwen2_5VLTemplate))
 
-register_template(QwenTemplateMeta(MLLMTemplateType.mimo_vl, template_cls=Qwen2_5VLTemplate,
-                                   default_system='You are MiMo, an AI assistant developed by Xiaomi.'))
+register_template(
+    QwenTemplateMeta(
+        MLLMTemplateType.mimo_vl,
+        template_cls=Qwen2_5VLTemplate,
+        default_system='You are MiMo, an AI assistant developed by Xiaomi.'))
+
 
 class Qwen2_5OmniTemplate(Qwen2_5VLTemplate):
     version = 'omni'

tests/test_align/test_template/test_llm.py

@@ -390,7 +390,7 @@ def test_gemma3():
 
 
 def test_mimo():
-    pt_engine = PtEngine('XiaomiMiMo/MiMo-7B-SFT')
+    pt_engine = PtEngine('XiaomiMiMo/MiMo-7B-RL-0530')
     res = _infer_model(pt_engine)
     pt_engine.default_template.template_backend = 'jinja'
     res2 = _infer_model(pt_engine)
@@ -426,7 +426,7 @@ def test_mimo():
     # test_phi4_mini()
     # test_internlm3()
     # test_deepseek_r1_distill()
-    test_deepseek_prover_v2()
+    # test_deepseek_prover_v2()
     # test_qwen2_5_prm()
     # test_mistral_small()
     # test_baichuan_m1()
@@ -435,4 +435,4 @@ def test_mimo():
     # test_gemma3()
     # test_glm4_0414()
     # test_qwen3()
-    # test_mimo()
+    test_mimo()