Update README.md

README.md

@@ -25,7 +25,7 @@ A fine-tuned version of the LLaMA 3.2B model using QLoRA on a custom League of L
 | Base Model                 | unsloth/Llama-3.2-3B-bnb-4bit     |
 | Epochs                     | 1                                 |
 | Max Steps                  | 4751                              |
-| Batch Size                 | 16 (per device)                   |
+| Batch Size                 | 16                                |
 | Max Sequence Length        | 1024                              |
 | Gradient Accumulation      | 1                                 |
 | Learning Rate              | 2e-4                              |
@@ -37,6 +37,19 @@ A fine-tuned version of the LLaMA 3.2B model using QLoRA on a custom League of L
 
 ---
 
+
+## 📏 Evaluation Metrics
+
+Evaluated using BLEU, ROUGE-L, and Exact Match on validation prompts.
+
+| Metric        | Value  |
+|---------------|--------|
+| BLEU          | 0.874 |
+| ROUGE-L       | 0.930 |
+
+---
+
+
 ## 📊 Final Training Metrics
 
 | Metric                     | Value                |
@@ -51,17 +64,6 @@ A fine-tuned version of the LLaMA 3.2B model using QLoRA on a custom League of L
 
 ---
 
-## 📏 Evaluation Metrics
-
-Evaluated using BLEU, ROUGE-L, and Exact Match on validation prompts.
-
-| Metric        | Value  |
-|---------------|--------|
-| BLEU          | 0.874 |
-| ROUGE-L       | 0.930 |
-
----
-
 ## ⚙️ Usage
 
 ```python
@@ -90,19 +92,10 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 - **Application**: Suggests champion item builds for League of Legends based on role.
 - **Limitations**:
-  - May suggest deprecated or invalid items.
+  - May suggest deprecated or invalid items if outdated.
+
+## Github
+
+- https://github.com/HatimFertat/lol_builds
 
----
 
-## 📦 Files Included
-
-| File                        | Purpose                        |
-|-----------------------------|--------------------------------|
-| adapter_model.safetensors  | LoRA adapter weights           |
-| adapter_config.json         | LoRA configuration             |
-| tokenizer_config.json       | Tokenizer settings             |
-| tokenizer.json              | Tokenizer vocabulary           |
-| generation_config.json      | Generation parameters          |
-| training_args.bin           | Training arguments snapshot    |
-| trainer_state.json          | Training/evaluation metrics    |
-| special_tokens_map.json     | Token mapping info             |