support deepseek-v3 (#2781)

modelscope · Dec 27, 2024 · 2776550 · 2776550
1 parent 1e2fda1
commit 2776550
Show file tree

Hide file tree

Showing 5 changed files with 12 additions and 1 deletion.
diff --git a/docs/source/Instruction/支持的模型和数据集.md b/docs/source/Instruction/支持的模型和数据集.md
@@ -344,6 +344,8 @@
 |[deepseek-ai/DeepSeek-V2-Chat](https://modelscope.cn/models/deepseek-ai/DeepSeek-V2-Chat)|deepseek_v2|deepseek|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V2-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat)|
 |[deepseek-ai/DeepSeek-V2.5](https://modelscope.cn/models/deepseek-ai/DeepSeek-V2.5)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V2.5](https://huggingface.co/deepseek-ai/DeepSeek-V2.5)|
 |[deepseek-ai/DeepSeek-V2.5-1210](https://modelscope.cn/models/deepseek-ai/DeepSeek-V2.5-1210)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V2.5-1210](https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210)|
+|[deepseek-ai/DeepSeek-V3-Base](https://modelscope.cn/models/deepseek-ai/DeepSeek-V3-Base)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V3-Base](https://huggingface.co/deepseek-ai/DeepSeek-V3-Base)|
+|[deepseek-ai/DeepSeek-V3](https://modelscope.cn/models/deepseek-ai/DeepSeek-V3)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3)|
 |[OpenBuddy/openbuddy-llama-65b-v8-bf16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama-65b-v8-bf16)|openbuddy_llama|openbuddy|-|-|[OpenBuddy/openbuddy-llama-65b-v8-bf16](https://huggingface.co/OpenBuddy/openbuddy-llama-65b-v8-bf16)|
 |[OpenBuddy/openbuddy-llama2-13b-v8.1-fp16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16)|openbuddy_llama|openbuddy|-|-|[OpenBuddy/openbuddy-llama2-13b-v8.1-fp16](https://huggingface.co/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16)|
 |[OpenBuddy/openbuddy-llama2-70b-v10.1-bf16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama2-70b-v10.1-bf16)|openbuddy_llama|openbuddy|-|-|[OpenBuddy/openbuddy-llama2-70b-v10.1-bf16](https://huggingface.co/OpenBuddy/openbuddy-llama2-70b-v10.1-bf16)|

diff --git a/docs/source_en/Instruction/Supported-models-and-datasets.md b/docs/source_en/Instruction/Supported-models-and-datasets.md
@@ -344,6 +344,8 @@ The table below introduces the models integrated with ms-swift:
 |[deepseek-ai/DeepSeek-V2-Chat](https://modelscope.cn/models/deepseek-ai/DeepSeek-V2-Chat)|deepseek_v2|deepseek|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V2-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat)|
 |[deepseek-ai/DeepSeek-V2.5](https://modelscope.cn/models/deepseek-ai/DeepSeek-V2.5)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V2.5](https://huggingface.co/deepseek-ai/DeepSeek-V2.5)|
 |[deepseek-ai/DeepSeek-V2.5-1210](https://modelscope.cn/models/deepseek-ai/DeepSeek-V2.5-1210)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V2.5-1210](https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210)|
+|[deepseek-ai/DeepSeek-V3-Base](https://modelscope.cn/models/deepseek-ai/DeepSeek-V3-Base)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V3-Base](https://huggingface.co/deepseek-ai/DeepSeek-V3-Base)|
+|[deepseek-ai/DeepSeek-V3](https://modelscope.cn/models/deepseek-ai/DeepSeek-V3)|deepseek_v2_5|deepseek_v2_5|transformers>=4.39.3|-|[deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3)|
 |[OpenBuddy/openbuddy-llama-65b-v8-bf16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama-65b-v8-bf16)|openbuddy_llama|openbuddy|-|-|[OpenBuddy/openbuddy-llama-65b-v8-bf16](https://huggingface.co/OpenBuddy/openbuddy-llama-65b-v8-bf16)|
 |[OpenBuddy/openbuddy-llama2-13b-v8.1-fp16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16)|openbuddy_llama|openbuddy|-|-|[OpenBuddy/openbuddy-llama2-13b-v8.1-fp16](https://huggingface.co/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16)|
 |[OpenBuddy/openbuddy-llama2-70b-v10.1-bf16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama2-70b-v10.1-bf16)|openbuddy_llama|openbuddy|-|-|[OpenBuddy/openbuddy-llama2-70b-v10.1-bf16](https://huggingface.co/OpenBuddy/openbuddy-llama2-70b-v10.1-bf16)|

diff --git a/swift/llm/model/model/deepseek.py b/swift/llm/model/model/deepseek.py
@@ -108,6 +108,8 @@ def _dtype_hook(module, input, output):
             ModelGroup([
                 Model('deepseek-ai/DeepSeek-V2.5', 'deepseek-ai/DeepSeek-V2.5'),
                 Model('deepseek-ai/DeepSeek-V2.5-1210', 'deepseek-ai/DeepSeek-V2.5-1210'),
+                Model('deepseek-ai/DeepSeek-V3-Base', 'deepseek-ai/DeepSeek-V3-Base'),
+                Model('deepseek-ai/DeepSeek-V3', 'deepseek-ai/DeepSeek-V3'),
             ]),
         ],
         TemplateType.deepseek_v2_5,

diff --git a/swift/llm/template/base.py b/swift/llm/template/base.py
@@ -610,6 +610,7 @@ def _encode(self, inputs: StdTemplateInputs) -> Dict[str, Any]:
         if (self.template_meta.template_type == 'dummy' and self.use_chat_template and not self.is_training
                 and self.mode != 'seq_cls'):
             template_backend = 'jinja'
+            logger.info_once(f'Setting template_backend: {template_backend}')
         res_context_list, loss_scale_list, answer_len = (
             self._swift_encode(inputs) if template_backend == 'swift' else self._jinja_encode(inputs))
         encoded = {}

diff --git a/tests/test_align/test_template/test_template.py b/tests/test_align/test_template/test_template.py
@@ -5,6 +5,9 @@ def test_deepseek_v2_5():
     tokenizer = get_model_tokenizer('deepseek-ai/DeepSeek-V2.5-1210', load_model=False)[1]
     template = get_template(tokenizer.model_meta.template, tokenizer)
     inputs = TemplateInputs(messages=[{
+        'role': 'system',
+        'content': '000'
+    }, {
         'role': 'user',
         'content': 'aaa'
     }, {
@@ -17,8 +20,9 @@ def test_deepseek_v2_5():
     res = template.encode(inputs)
     template.print_inputs(res)
     template.template_backend = 'jinja'
-    res = template.encode(inputs)
+    res2 = template.encode(inputs)
     template.print_inputs(res)
+    assert res['input_ids'] == res2['input_ids']
 
 
 if __name__ == '__main__':