Update README.md

README.md

@@ -10,12 +10,10 @@ language:
 - en
 ---
 
-# Uploaded finetuned  model
+## ⚠️ Preview Status
 
-- **Developed by:** Jackrong
-- **License:** apache-2.0
-- **Finetuned from model :** qwen/Qwen3.5-9B
+This repository is currently a **preview release**.
 
-This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+The model is still under active testing, and I am continuing to explore more suitable training settings and optimization strategies. Because of this, the current version should be considered **experimental**.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+Downloading or using this model for serious evaluation is **not recommended yet**. A more stable version will be released after further testing and parameter tuning.