support deepseek_prover_v2 (#4184)

Author: Jintao-Huang

docs/source/Instruction/支持的模型和数据集.md

@@ -394,6 +394,8 @@
 |[deepseek-ai/DeepSeek-V3-0324](https://modelscope.cn/models/deepseek-ai/DeepSeek-V3-0324)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324)|
 |[cognitivecomputations/DeepSeek-V3-awq](https://modelscope.cn/models/cognitivecomputations/DeepSeek-V3-awq)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[cognitivecomputations/DeepSeek-V3-AWQ](https://huggingface.co/cognitivecomputations/DeepSeek-V3-AWQ)|
 |[cognitivecomputations/DeepSeek-V3-0324-AWQ](https://modelscope.cn/models/cognitivecomputations/DeepSeek-V3-0324-AWQ)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[cognitivecomputations/DeepSeek-V3-0324-AWQ](https://huggingface.co/cognitivecomputations/DeepSeek-V3-0324-AWQ)|
+|[deepseek-ai/DeepSeek-Prover-V2-7B](https://modelscope.cn/models/deepseek-ai/DeepSeek-Prover-V2-7B)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-Prover-V2-7B](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-7B)|
+|[deepseek-ai/DeepSeek-Prover-V2-671B](https://modelscope.cn/models/deepseek-ai/DeepSeek-Prover-V2-671B)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-Prover-V2-671B](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B)|
 |[deepseek-ai/DeepSeek-R1](https://modelscope.cn/models/deepseek-ai/DeepSeek-R1)|deepseek_r1|deepseek_r1|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)|
 |[deepseek-ai/DeepSeek-R1-Zero](https://modelscope.cn/models/deepseek-ai/DeepSeek-R1-Zero)|deepseek_r1|deepseek_r1|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-R1-Zero](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero)|
 |[cognitivecomputations/DeepSeek-R1-awq](https://modelscope.cn/models/cognitivecomputations/DeepSeek-R1-awq)|deepseek_r1|deepseek_r1|transformers>=4.39.3|✘|-|[cognitivecomputations/DeepSeek-R1-AWQ](https://huggingface.co/cognitivecomputations/DeepSeek-R1-AWQ)|

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

@@ -394,6 +394,8 @@ The table below introduces the models integrated with ms-swift:
 |[deepseek-ai/DeepSeek-V3-0324](https://modelscope.cn/models/deepseek-ai/DeepSeek-V3-0324)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324)|
 |[cognitivecomputations/DeepSeek-V3-awq](https://modelscope.cn/models/cognitivecomputations/DeepSeek-V3-awq)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[cognitivecomputations/DeepSeek-V3-AWQ](https://huggingface.co/cognitivecomputations/DeepSeek-V3-AWQ)|
 |[cognitivecomputations/DeepSeek-V3-0324-AWQ](https://modelscope.cn/models/cognitivecomputations/DeepSeek-V3-0324-AWQ)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[cognitivecomputations/DeepSeek-V3-0324-AWQ](https://huggingface.co/cognitivecomputations/DeepSeek-V3-0324-AWQ)|
+|[deepseek-ai/DeepSeek-Prover-V2-7B](https://modelscope.cn/models/deepseek-ai/DeepSeek-Prover-V2-7B)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-Prover-V2-7B](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-7B)|
+|[deepseek-ai/DeepSeek-Prover-V2-671B](https://modelscope.cn/models/deepseek-ai/DeepSeek-Prover-V2-671B)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-Prover-V2-671B](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B)|
 |[deepseek-ai/DeepSeek-R1](https://modelscope.cn/models/deepseek-ai/DeepSeek-R1)|deepseek_r1|deepseek_r1|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)|
 |[deepseek-ai/DeepSeek-R1-Zero](https://modelscope.cn/models/deepseek-ai/DeepSeek-R1-Zero)|deepseek_r1|deepseek_r1|transformers>=4.39.3|✘|-|[deepseek-ai/DeepSeek-R1-Zero](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero)|
 |[cognitivecomputations/DeepSeek-R1-awq](https://modelscope.cn/models/cognitivecomputations/DeepSeek-R1-awq)|deepseek_r1|deepseek_r1|transformers>=4.39.3|✘|-|[cognitivecomputations/DeepSeek-R1-AWQ](https://huggingface.co/cognitivecomputations/DeepSeek-R1-AWQ)|

swift/llm/model/model/deepseek.py

@@ -110,7 +110,11 @@ def get_model_tokenizer_deepseek_moe(model_dir: str,
             ModelGroup([
                 Model('cognitivecomputations/DeepSeek-V3-awq', 'cognitivecomputations/DeepSeek-V3-AWQ'),
                 Model('cognitivecomputations/DeepSeek-V3-0324-AWQ', 'cognitivecomputations/DeepSeek-V3-0324-AWQ')
-            ])
+            ]),
+            ModelGroup([
+                Model('deepseek-ai/DeepSeek-Prover-V2-7B', 'deepseek-ai/DeepSeek-Prover-V2-7B'),
+                Model('deepseek-ai/DeepSeek-Prover-V2-671B', 'deepseek-ai/DeepSeek-Prover-V2-671B'),
+            ]),
         ],
         TemplateType.deepseek_v2_5,
         get_model_tokenizer_deepseek_moe,

tests/test_align/test_template/test_llm.py

@@ -302,6 +302,14 @@ def test_deepseek_r1_distill():
     assert res == res2, f'res: {res}, res2: {res2}'
 
 
+def test_deepseek_prover_v2():
+    pt_engine = PtEngine('deepseek-ai/DeepSeek-Prover-V2-7B')
+    res = _infer_model(pt_engine)
+    pt_engine.default_template.template_backend = 'jinja'
+    res2 = _infer_model(pt_engine)
+    assert res == res2, f'res: {res}, res2: {res2}'
+
+
 def test_qwen2_5_prm():
     pt_engine = PtEngine('Qwen/Qwen2.5-Math-7B-PRM800K')
     data = {
@@ -418,6 +426,7 @@ def test_mimo():
     # test_phi4_mini()
     # test_internlm3()
     # test_deepseek_r1_distill()
+    test_deepseek_prover_v2()
     # test_qwen2_5_prm()
     # test_mistral_small()
     # test_baichuan_m1()
@@ -426,4 +435,4 @@ def test_mimo():
     # test_gemma3()
     # test_glm4_0414()
     # test_qwen3()
-    test_mimo()
+    # test_mimo()