Update README.md

README.md

@@ -50,6 +50,8 @@ For more details, including benchmark evaluation, hardware requirements, and inf
 
 ## Usage
 
+📌 **Tip**: We recommend that developers customize the `instruct` according to their specific scenarios, tasks, and languages. Our tests have shown that in most retrieval scenarios, not using an `instruct` on the query side can lead to a drop in retrieval performance by approximately 1% to 5%.
+
 ### llama.cpp
 Check out our [llama.cpp documentation](https://qwen.readthedocs.io/en/latest/run_locally/llama.cpp.html) for more usage guide.
 
@@ -59,7 +61,7 @@ In the following demonstration, we assume that you are running commands under th
 You can run Qwen3 Embedding with one command:
 
 ```shell
-./build/bin/llama-embedding -m model.gguf  -p "<your context here>"  --pooling last --verbose-prompt --embd-normalize -1 
+./build/bin/llama-embedding -m model.gguf  -p "<your context here><|endoftext|>"  --pooling last --verbose-prompt --embd-normalize 2
 ```
 
 Or lunch a server:
@@ -67,6 +69,10 @@ Or lunch a server:
 ./build/bin/llama-server -m model.gguf --embedding --pooling last -ub 8192 --verbose-prompt
 ```
 
+📌 **Tip**: Qwen3 Embedding models default to using the last token as `<|endoftext|>`, so you need to manually append this token to the end of your own input context. In addition, when running the `llama-server`, you also need to manually normalize the output embeddings as `llama-server` currently does not support the `--embd-normalize` option.
+
+
+
 ## Evaluation
 
 ### MTEB (Multilingual)