Update README.md

README.md

@@ -10,12 +10,16 @@ language:
 - en
 ---
 
-# Uploaded finetuned  model
+# Gemma-3-270M-LeetCode
 
-- **Developed by:** Codingstark
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-3-270m-it
+A specialized fine-tuned Gemma-3-270M model optimized for LeetCode algorithmic programming problems.
 
-This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## Features
+- **270M parameters** - Compact yet powerful
+- **2,641 training examples** - Curated LeetCode dataset
+- **Dual format** - HuggingFace & GGUF compatible
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## Performance
+- Training loss: 1.035 → 0.986
+- Memory usage: 2.76GB peak
+- Inference: temperature=1.0, top_p=0.95, top_k=64