Update README.md

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: unsloth/meta-llama-3.1-8b-bnb-4bit
 tags:
-- text-generation-inference
-- transformers
+- text-generation
+- sql-generation
+- finetuning
+- lora
+- peft
 - unsloth
 - llama
 license: apache-2.0
@@ -10,12 +13,92 @@ language:
 - en
 ---
 
-# Uploaded finetuned  model
+# SQL-Genie (LLaMA-3.1-8B Fine-Tuned)
 
-- **Developed by:** dhashu
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/meta-llama-3.1-8b-bnb-4bit
+## Model Overview
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+**SQL-Genie** is a fine-tuned version of **LLaMA-3.1-8B**, specialized for **natural language to SQL generation**.  
+The model was trained using **parameter-efficient fine-tuning (LoRA)** on a structured SQL instruction dataset, enabling accurate SQL query generation while keeping training and inference costs low.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+- **Developed by:** dhashu  
+- **Base model:** `unsloth/meta-llama-3.1-8b-bnb-4bit`  
+- **License:** Apache-2.0  
+- **Training framework:** Unsloth + Hugging Face TRL  
+
+---
+
+## Training Methodology
+
+This model was fine-tuned using **LoRA (Low-Rank Adaptation)** via the **PEFT** framework.
+
+### Key Training Details
+- Base model loaded in **4-bit quantization** for memory efficiency
+- **LoRA adapters** applied to attention and feed-forward layers
+- Base model weights remained **frozen**
+- Only LoRA parameters were trained
+- Training performed using **Supervised Fine-Tuning (SFT)**
+
+This approach allows the model to learn SQL generation patterns efficiently without full model retraining.
+
+---
+
+## Dataset
+
+The model was trained on a subset of the **`b-mc2/sql-create-context`** dataset, which contains:
+- Natural language questions
+- Database schema/context
+- Corresponding SQL queries
+
+Each sample was formatted as an instruction-style prompt to improve reasoning and output structure.
+
+---
+
+## Performance & Efficiency
+
+- 🚀 **2× faster fine-tuning** using **Unsloth**
+- 💾 **Low VRAM usage** via 4-bit quantization
+- 🧠 Improved schema understanding and SQL syntax generation
+- ⚡ Suitable for real-time inference and lightweight deployments
+
+---
+
+## Model Variants
+
+This repository may contain **either**:
+
+### 🔹 LoRA Adapter Model
+- Contains only LoRA weights
+- Requires loading the base LLaMA-3.1-8B model
+- Ideal for research and modular fine-tuning
+
+### 🔹 Merged Model (if applicable)
+- LoRA adapters merged into base weights
+- No PEFT required at inference time
+- Ready-to-use single checkpoint
+
+(Check the repository files to confirm the variant.)
+
+---
+
+## Intended Use Cases
+
+- Natural language → SQL query generation
+- Database querying assistants
+- AI-powered analytics tools
+- Educational and research purposes
+
+---
+
+## Limitations
+
+- Trained on a limited SQL dataset subset
+- Not guaranteed to generalize to all SQL dialects
+- Should be validated before production database usage
+
+---
+
+## Acknowledgements
+
+This model was trained using **Unsloth**, enabling faster and more memory-efficient fine-tuning of large language models.
+
+[![Made with Unsloth](https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png)](https://github.com/unslothai/unsloth)