Update README.md

README.md

@@ -96,7 +96,12 @@ This model was trained using LoRA available through the [PEFT library](https://g
 ### Using Transformers
 This uses the merged weights (base model weights + LoRA weights) to allow for simple use in Transformers pipelines. It has the same performance as using the weights separately when using the PEFT library.
 ```python
-from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
+import torch
+from transformers import(
+  AutoModelForQuestionAnswering,
+  AutoTokenizer,
+  pipeline
+)
 model_name = "sjrhuschlee/deberta-v3-large-squad2"
 
 # a) Using pipelines
@@ -106,10 +111,25 @@ qa_input = {
 'context': 'My name is Sarah and I live in London'
 }
 res = nlp(qa_input)
+# {'score': 0.984, 'start': 30, 'end': 37, 'answer': ' London'}
 
 # b) Load model & tokenizer
 model = AutoModelForQuestionAnswering.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+question = 'Where do I live?'
+context = 'My name is Sarah and I live in London'
+encoding = tokenizer(question, context, return_tensors="pt")
+start_scores, end_scores = model(
+  encoding["input_ids"],
+  attention_mask=encoding["attention_mask"],
+  return_dict=False
+)
+
+all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0].tolist())
+answer_tokens = all_tokens[torch.argmax(start_scores):torch.argmax(end_scores) + 1]
+answer = tokenizer.decode(tokenizer.convert_tokens_to_ids(answer_tokens))
+# 'London'
 ```
 
 ### Using with Peft