Update README.md

README.md

@@ -14,17 +14,46 @@ Optimized models are published here in [ONNX](https://onnx.ai) format to run wit
 
 To easily get started with the model, you can use our ONNX Runtime Generate() API. See instructions [here](https://github.com/microsoft/onnxruntime/blob/gh-pages/docs/genai/tutorials/deepseek-python.md)
 
+For CPU:
+
 ```bash
-# Download the model directly using the huggingface cli
-huggingface-cli download onnxruntime/DeepSeek-R1-Distill-ONNX --include 'deepseek-r1-distill-qwen-1.5B/*' --local-dir .
+# Download the model directly using the Hugging Face CLI
+huggingface-cli download onnxruntime/DeepSeek-R1-Distill-ONNX --include 'deepseek-r1-distill-qwen-1.5B/cpu_and_mobile/*' --local-dir .
+
+# Install the CPU package of ONNX Runtime GenAI
+pip install onnxruntime-genai
+
+# Please adjust the model directory (-m) accordingly 
+curl -o https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/model-chat.py
+python model-chat.py -m /path/to/cpu-int4-rtn-block-32-acc-level-4/ -e cpu --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"
 ```
 
+For CUDA:
+
 ```bash
-pip install --pre onnxruntime-genai
+# Download the model directly using the Hugging Face CLI
+huggingface-cli download onnxruntime/DeepSeek-R1-Distill-ONNX --include 'deepseek-r1-distill-qwen-1.5B/cuda/*' --local-dir .
+
+# Install the CUDA package of ONNX Runtime GenAI
+pip install onnxruntime-genai-cuda
+
+# Please adjust the model directory (-m) accordingly 
+curl -o https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/model-chat.py
+python model-chat.py -m /path/to/cuda-int4-rtn-block-32/ -e cuda --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"
+```
+
+For DirectML:
+
+```bash
+# Download the model directly using the Hugging Face CLI
+huggingface-cli download onnxruntime/DeepSeek-R1-Distill-ONNX --include 'deepseek-r1-distill-qwen-1.5B/directml/*' --local-dir .
+
+# Install the DirectML package of ONNX Runtime GenAI
+pip install onnxruntime-genai-directml
 
-# CPU Chat inference. If you pulled the model from huggingface, adjust the model directory (-m) accordingly 
+# Please adjust the model directory (-m) accordingly 
 curl -o https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/model-chat.py
-python model-chat.py -m deepseek-r1-distill-qwen-1.5B/model -e cpu --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"
+python model-chat.py -m /path/to/directml-int4-rtn-block-32/ -e dml --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"
 ```
 
 ## ONNX Models