Update README.md

README.md

@@ -42,7 +42,7 @@ https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct
 **Image Process**
 |Chips| input size | image num | image encoder | ttft(320 tokens) | w8a16 | DDR | Flash |
 |--|--|--|--|--|--|--|--|
-|AX650| 448*448 | 1 | 780 ms | 420 ms | 6.2 tokens/sec| 4.3 GiB |  4.6 GiB  |
+|AX650| 448*448 | 1 | 780 ms | 2857 ms | 6.2 tokens/sec| 4.3 GiB |  4.6 GiB  |
 
 **Video Process**
 |Chips| input size | image num | image encoder |ttft(512 tokens) | w8a16 | DDR | Flash |
@@ -104,15 +104,25 @@ root@ax650:/mnt/qtang/llm-test/qwen2.5-vl-3b# tree -L 2
 
 ```
 
+### Prepare tokenizer server
+
 #### Install transformer
 
 ```
 pip install transformers==4.41.1
 ```
 
-#### Start the Tokenizer service
+### Demo Run
+
+#### Image understand demo
+
+##### start tokenizer server for image understand demo
+
+```
+python3 qwen2_tokenizer_image_448.py --port 12345
+```
 
-**If you using image process**
+##### run image understand demo
 
 - input text
 
@@ -156,10 +166,18 @@ image >> image/ssd_car.jpg
 [N][                             Run][ 779]: hit eos,avg 5.96 token/s
 ```
 
-**If you using video process**
+#### Video understand demo
 
 Please pre-process the image of the video file into a 308x308 size picture
 
+##### start tokenizer server for image understand demo
+
+```
+python qwen2_tokenizer_video_308.py --port 12345
+```
+
+##### run image understand demo
+
 ```
 root@ax650:/mnt/qtang/llm-test/qwen2.5-vl-3b# ./run_qwen2_5_vl_video.sh
 [I][                            Init][ 129]: LLM init start