Update README.md

README.md

@@ -7,17 +7,15 @@ tags:
 - gemma2
 - trl
 - sft
-license: apache-2.0
+license: gemma
 language:
 - en
 ---
 
-# Uploaded  model
+# This model is trained by Unsloth. This is the commission from my friend to improve the writing styles of lemon07r/Gemma-2-Ataraxy-v4d-9B in his native languages. 
 
-- **Developed by:** Alsebay
-- **License:** apache-2.0
-- **Finetuned from model :** lemon07r/Gemma-2-Ataraxy-v4d-9B
+- 3rd version, fixed the issue that talk for {{user}}.
+- Know issue: Short response, but longer than v2 and v1, for english only is ok.
+- Pros: Long response in english, good writing styles?
+- Cons: Target native language styles and gammar is not too good, also short response in Vietnamese, Chinese, Japanese due to the dataset is novel chapter, short sentence in 1 row. :/.
 
-This gemma2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)