Update README.md

README.md

@@ -1,8 +1,7 @@
 ---
 license: apache-2.0
 ---
-# X-LoRA
-Mixture of LoRA Experts: Leverage the power of fine-tuned LoRA experts by employing a mixture of experts, or MoE technique.
+# X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models 
 
 X-LoRA works by learning scaling values for LoRA adapters. These learned scalings values are used to
 gate the LoRA experts in a dense fashion. Additionally, all LoRA adapters and the base model are frozen, allowing efficient fine tuning due to a low parameter count.
@@ -154,12 +153,16 @@ output_text=generate_response (model, tokenizer, text_input=txt,eos_token_id=eos
 print (output_text[0])
 ```
 
+## Acknowledgements
+
+This work is built on the Hugging Face [PEFT library](https://github.com/huggingface/peft/tree/main/src/peft) and other components in the Hugging Face ecosystem. 
+
 ## Original paper and citation
 
 Cite this work as:
 ```bibtex
 @article{NiBuehler_2024,
-    title   = {X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Mixture-of-Experts Framework for Large Language Models with Applications in Protein Mechanics and Design},
+    title   = {X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Design},
     author  = {E.L. Buehler, M.J. Buehler},
     journal = {},
     year    = {2024},