Update README.md

README.md

@@ -18,6 +18,8 @@ tags:
 
 This is the [deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) model, fine-tuned using the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Extractive Question Answering.
 
+This model was trained using LoRA available through the [PEFT library](https://github.com/huggingface/peft).
+
 ## Overview
 **Language model:** deberta-v3-large  
 **Language:** English  
@@ -28,13 +30,6 @@ This is the [deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large
 
 ## Model Usage
 
-### Using with Peft
-```python
-from peft import LoraConfig, PeftModelForQuestionAnswering
-from transformers import AutoModelForQuestionAnswering, AutoTokenizer
-model_name = "sjrhuschlee/deberta-v3-large-squad2"
-```
-
 ### Using the Merged Model
 ```python
 from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
@@ -51,4 +46,14 @@ res = nlp(qa_input)
 # b) Load model & tokenizer
 model = AutoModelForQuestionAnswering.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
+```
+
+### Using with Peft
+**NOTE**: This requires code in the PR https://github.com/huggingface/peft/pull/473 for the PEFT library.
+```python
+#!pip install peft
+
+from peft import LoraConfig, PeftModelForQuestionAnswering
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer
+model_name = "sjrhuschlee/deberta-v3-large-squad2"
 ```