Update README.md

README.md

@@ -1,61 +1,72 @@
 ---
 language:
-- en
+    - en
 license: apache-2.0
 base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
 tags:
-- code
-- python
-- educational
-- lora
-- qwen
+    - code
+    - python
+    - educational
+    - lora
+    - qwen
 library_name: peft
 ---
 
 # Qwen2.5-Coder-1.5B-Educational (LoRA)
 
-LoRA adapter for [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) fine-tuned on educational code generation.
+LoRA adapter for [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct), fine-tuned for educational code generation.
 
-## Quick Start
+---
+
+## 🚀 Quick Start
 
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 
 # Load base model
 base_model = AutoModelForCausalLM.from_pretrained(
-"Qwen/Qwen2.5-Coder-1.5B-Instruct",
-device_map="auto"
+        "Qwen/Qwen2.5-Coder-1.5B-Instruct",
+        device_map="auto"
 )
 
 # Load LoRA adapter
-model = PeftModel.from_pretrained(base_model, "YOUR_USERNAME/qwen-coder-1.5b-educational")
-tokenizer = AutoTokenizer.from_pretrained("YOUR_USERNAME/qwen-coder-1.5b-educational")
+model = PeftModel.from_pretrained(base_model, "Beebey/qwen-coder-1.5b-educational")
+tokenizer = AutoTokenizer.from_pretrained("Beebey/qwen-coder-1.5b-educational")
 
 # Generate code
-prompt = "Instruction: Write a Python function to reverse a string
-Réponse:
-"
+prompt = (
+        "Instruction: Write a Python function to reverse a string\n"
+        "Réponse:\n"
+)
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=200)
-print(tokenizer.decode(outputs, skip_special_tokens=True))
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
-## Training Details
+---
 
-- **Method**: LoRA (r=8, alpha=16, dropout=0.05)
-- **Dataset**: OpenCoder-LLM/opc-sft-stage2 (educational_instruct)
-- **Steps**: 2000
-- **Final Loss**: 0.530
-- **Hardware**: TPU v6e-16
-- **Training Time**: 43 minutes
+## 🏋️ Training Details
 
-## Performance
+- **Method:** LoRA (r=8, alpha=16, dropout=0.05)
+- **Dataset:** [OpenCoder-LLM/opc-sft-stage2](https://huggingface.co/datasets/OpenCoder-LLM/opc-sft-stage2) (`educational_instruct`)
+- **Steps:** 2000
+- **Final Loss:** 0.530
+- **Hardware:** TPU v6e-16
+- **Training Time:** 43 minutes
 
-Improved over base model on:
+---
+
+## 📈 Performance
+
+Enhanced capabilities for:
 - Educational Python code generation
 - Pythonic idioms and patterns
 - Object-oriented architecture
 - Code documentation and comments
 
-## License
+---
+
+## 📄 License
 
-Apache 2.0
+Apache 2.0