Update README.md

README.md

@@ -17,9 +17,9 @@ tags:
 - code
 ---
 
-# **rStar-Coder-Qwen3(exp)**
+# **rStar-Coder-Qwen3**
 
-> *rStar-Coder-Qwen3* is a high-efficiency, multi-domain model fine-tuned on *Qwen3-4B* using the **rStar-Coder** dataset enhanced with **code, math, and science expert clusters** and an extended **open code reasoning dataset**. This model blends symbolic precision, scientific logic, and structured output fluency—making it an ideal tool for developers, educators, and researchers seeking advanced reasoning under constrained compute.
+> rStar-Coder-Qwen3 is a high-efficiency, multi-domain model fine-tuned on **Qwen-0.6B** using the **rStar-Coder** dataset enhanced with **code expert clusters** and an extended **open code reasoning dataset**. This model blends symbolic precision, scientific logic, and structured output fluency—making it an ideal tool for developers, educators, and researchers seeking advanced reasoning under constrained compute.
 
 > \[!note]
 > GGUF: [https://huggingface.co/prithivMLmods/rStar-Coder-Qwen3-GGUF](https://huggingface.co/prithivMLmods/rStar-Coder-Qwen3-GGUF)
@@ -43,11 +43,26 @@ tags:
 5. **Structured Output Mastery**
    Seamlessly generates output in **LaTeX**, **Markdown**, **JSON**, **CSV**, and **YAML**, suited for research reports, technical documentation, and data formats.
 
-6. **Optimized 4B Footprint for Versatile Deployment**
+6. **Optimized Lightweight Footprint for Versatile Deployment**
    Strikes a balance between performance and efficiency, making it deployable on **mid-range GPUs**, **offline clusters**, and advanced **edge AI systems**.
 
 ---
 
+## Dataset Seed
+
+```python
+from datasets import load_dataset
+
+# Load the reasoning dataset
+reasoning_dataset = load_dataset(
+    "microsoft/rStar-Coder",
+    data_files="seed_sft/data-00001-of-00020.parquet",
+    split="train"
+)
+```
+
+---
+
 ## **Quickstart with Transformers**
 
 ```python
@@ -91,21 +106,6 @@ print(response)
 
 ---
 
-## **Dataset Seed**
-
-```python
-from datasets import load_dataset
-
-# Load the reasoning dataset
-reasoning_dataset = load_dataset(
-    "microsoft/rStar-Coder",
-    data_files="seed_sft/data-00001-of-00020.parquet",
-    split="train"
-)
-```
-
----
-
 ## **Intended Use**
 
 * Scientific tutoring, computational logic, and mathematical education
@@ -121,10 +121,8 @@ reasoning_dataset = load_dataset(
 * Specialized in technical and symbolic tasks—general chat may underperform
 * Prioritizes structured reasoning over emotional or casual tone generation
 
----
-
 ## **References**
 
 1. [Qwen2.5 Technical Report (2024)](https://arxiv.org/pdf/2412.15115)
 2. [YaRN: Efficient Context Window Extension of Large Language Models](https://arxiv.org/pdf/2309.00071)
-3. [rStar-Coder Dataset](https://huggingface.co/datasets/microsoft/rStar-Coder)
+3. [microsoft/rStar-Coder Dataset](https://huggingface.co/datasets/microsoft/rStar-Coder)