Update README.md

README.md

@@ -41,11 +41,15 @@ metrics:
     <a href="https://colab.research.google.com/drive/1ze7qAQnjppZKfxNVBXXlOBTM6xFWEYrJ?usp=sharing" target="_blank" style="margin: 2px;">
         <img alt="Gradio-Colab" src="https://img.shields.io/badge/Gradio-Colab-0084FF?style=for-the-badge&logo=gradio&labelColor=F9AB00" style="display: inline-block; vertical-align: middle;">
     </a>
-    <a href="https://arxiv.org/abs/Your_Paper_ID" target="_blank" style="margin: 2px;">
-        <img alt="arXiv Paper" src="https://img.shields.io/badge/arXiv-Preprint-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white" style="display: inline-block; vertical-align: middle;">
+    <a href="https://doi.org/10.6084/m9.figshare.12345678" target="_blank" style="margin: 2px;">
+        <img alt="Figshare" src="https://img.shields.io/badge/Figshare-DOI-0085CA?style=for-the-badge&logo=figshare&logoColor=white" style="display: inline-block; vertical-align: middle;">
     </a>
 </div>
 
+<p align="center">
+  <a href="https://doi.org/10.6084/m9.figshare.12345678"><b>Paper Link</b>👁️</a>
+</p>
+
 ## Abstract
 State-of-the-art advances in LLMs have pushed NLP to its limits, where even complex tasks, such as code generation, can be automated. This paper describes the deepSQL-R1-distill-8B, a fine-tuned and quantized model variant of the DeepSeek-R1 model architecture and specifically optimized for text-to-SQL conversion. Fine-tuning was performed using Unsloth, one of the most efficient frameworks for fine-tuning LLMs, in combination with Parameter-Efficient Fine-Tuning and the SFTTrainer framework. This allows domain-specific adaptation with minimal resource consumption. The approach fine-tunes curated datasets by LoRA, ensuring a more parameter-efficient and lower-memory-consuming model. Besides this, we investigate reinforcement learning techniques to further enhance the model's ability in generating accurate and contextually appropriate SQL queries. Combination of 8-bit quantization, LoRA, Unsloth, and reinforcement learning places deepSQL-R1-distill-8B as one of the cutting-edge solutions for automatic SQL code generation in real-world applications.  Addressing major challenges in computational efficiency, domain-specific adaptation, and reinforcement-based refinement, this model is leading the way toward a more intuitive and resource-effective way of interacting with relational databases.
 
@@ -197,6 +201,7 @@ _ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=350)
   author = {Sanjoy Kumar},
   title = {DeepSQL-R1: A Quantized LLM for High-Performance and Reinforcement Driven NL2SQL Generation},
   year = {2025},
+  Paper = {https://doi.org/10.6084/m9.figshare.28330301.v1},
   Model Link = {https://huggingface.co/imsanjoykb/deepSQL-R1-distill-8B},
 }
 ```