diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/README.md b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/README.md
index 4a4990c1..b7443017 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/README.md
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/README.md
@@ -11,6 +11,7 @@ In this directory, you will find a C++ example on how to run LLM models on Intel
 | Qwen2 | [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct), [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) |
 | Qwen2.5 | [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) |
 | MiniCPM | [openbmb/MiniCPM-1B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-1B-sft-bf16), [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) |
+| DeepSeek-R1 | [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B), [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) |
 
 Please refer to [Quickstart](../../../../../../../docs/mddocs/Quickstart/npu_quickstart.md#c-api) for details about verified platforms.
 
@@ -72,6 +73,12 @@ python convert.py --repo-id-or-model-path openbmb/MiniCPM-1B-sft-bf16 --save-di
 
 :: to convert MiniCPM-2B-sft-bf16
 python convert.py --repo-id-or-model-path openbmb/MiniCPM-2B-sft-bf16 --save-directory <converted_model_path>
+
+:: to convert DeepSeek-R1-Distill-Qwen-1.5B
+python convert.py --repo-id-or-model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B  --save-directory <converted_model_path>
+
+:: to convert DeepSeek-R1-Distill-Qwen-7B
+python convert.py --repo-id-or-model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-7B  --save-directory <converted_model_path>
 ```
 
 Arguments info:
diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/llama-cli-npu.cpp b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/llama-cli-npu.cpp
index f4254170..9ad0f94c 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/llama-cli-npu.cpp
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/llama-cli-npu.cpp
@@ -34,6 +34,7 @@ const std::string llama2_template = "<s>[INST] <<SYS>>\n\n<</SYS>>\n\n%s [/INST]
 const std::string llama3_template = "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n%s<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n";
 const std::string minicpm_template = "<用户>%s<AI>";
 const std::string qwen2_template = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n%s<|im_end|>\n<|im_start|>assistant\n";
+const std::string qwen2_deepseek_template = "<｜begin▁of▁sentence｜><｜begin▁of▁sentence｜>You are a helpful assistant.<｜User｜>%s<｜Assistant｜>";
 
 
 std::string add_chat_history(npu_model_params model_params,
@@ -66,6 +67,20 @@ std::string add_chat_history(npu_model_params model_params,
                 sprintf_s(prompt, res_template.c_str(), chat_history.c_str(), new_prompt.c_str());
             }
         }
+    } else if (model_params.model_type == std::string("qwen2") && model_params.max_position_embeddings == 131072) {
+        // For DeepSeek-R1
+        if (chat_history == ""){
+            sprintf_s(prompt, qwen2_deepseek_template.c_str(), new_prompt.c_str());
+        }else{
+            if (is_input){
+                std::string input_template = "%s%s<｜Assistant｜>";
+                sprintf_s(prompt, input_template.c_str(), chat_history.c_str(), new_prompt.c_str());
+            }
+            else{
+                std::string res_template = "%s%s<｜User｜>";
+                sprintf_s(prompt, res_template.c_str(), chat_history.c_str(), new_prompt.c_str());
+            }
+        }
     } else if (model_params.model_type == std::string("qwen2")) {
         if (chat_history == ""){
             sprintf_s(prompt, qwen2_template.c_str(), new_prompt.c_str());