Update README.md

README.md

@@ -16,7 +16,10 @@ datasets:
 QLoRA adapter for TinyLlama fine-tuned for 5 epochs on kaitchup/hellaswag_winograndexl_ai2_arc_correctAnswerOnly_flattened.
 
 The details on how this model was created:
-To be published.
+
+[Contaminated LLMs: What Happens When You Train an LLM on the Evaluation Benchmarks?](https://thesalt.substack.com/p/contaminated-llms-what-happens-when)
+
+
 
 
 ### Model Description