Update README.md

README.md

@@ -32,7 +32,22 @@ RobotAI: (1.0, -0.3)
     
 
 ## ℹ️ Usage
-1. DownLoad [Model]() and Follow [Qwen.cpp](https://github.com/QwenLM/qwen.cpp.git) get model.bin and qwen.tiktoken.
+1. DownLoad 🤗 [Model](https://huggingface.co/FreedomIntelligence/EmbodyAICar) get model.bin.
+   ```
+   cd EmbodyAICar
+   git submodule update --init --recursive
+   python qwen_cpp/convert.py -i {Model_Path} -t {type} -o robot1_8b-ggml.bin
+   ```
+   You are free to try any of the below quantization types by specifying -t <type>:
+
+    - q4_0: 4-bit integer quantization with fp16 scales.
+    - q4_1: 4-bit integer quantization with fp16 scales and minimum values.
+    - q5_0: 5-bit integer quantization with fp16 scales.
+    - q5_1: 5-bit integer quantization with fp16 scales and minimum values.
+    - q8_0: 8-bit integer quantization with fp16 scales.
+    - f16: half precision floating point weights without quantization.
+    - f32: single precision floating point weights without quantization.
+
 2. Install package serial.tar.gz
    ```
     cd serial
@@ -44,6 +59,7 @@ RobotAI: (1.0, -0.3)
     cmake --build build -j --config Release
     ```
 4. Now you may chat and control your AI car with the quantized RobotAI model by running:
+   - qwen.tiktoken is in the model directory
    ```
    ./build/bin/main -m robot1_8b-ggml.bin --tiktoken qwen.tiktoken -p 请快速向前
    ```
@@ -79,6 +95,5 @@ Please use the following citation if you intend to use our dataset for training
 }
 ```
 
-
 ## 🤖 Acknowledgement 
-- We thank [Qwen.cpp](https://github.com/QwenLM/qwen.cpp.git) and [llama.cpp](https://github.com/ggerganov/llama.cpp) for their excellent work.
+- We thank [Qwen.cpp](https://github.com/QwenLM/qwen.cpp.git) and [llama.cpp](https://github.com/ggerganov/llama.cpp) for their excellent work.