Hugging Face's logo

LDKSolutions
/
chatgpt-qa-detector-deberta-v3-large

Transformers
PyTorch
deberta-v2
Model card Files Community
1
Lukekim commited on
Commit
7523751
·
1 Parent(s): fed4d7a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -4,7 +4,9 @@ license: apache-2.0
4
 
5
  Detects if ChatGPT generated the answer given a prompt and answer pair (QA).
6
 
7
- [DeBERTa-v3-Large model](microsoft/deberta-v3-large) fine-tuned on [GPT Wiki intro](https://huggingface.co/datasets/aadityaubhat/GPT-wiki-intro) and [HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3) dataset.
 
 
8
 
9
  Fine-tuning was done for 1 epoch with 8:2 train/validation split. Recorded a validation accuracy of 99% for both GPT Wiki intro and HC3 after the 1st epoch.
10
 
 
4
 
5
  Detects if ChatGPT generated the answer given a prompt and answer pair (QA).
6
 
7
+ [DeBERTa-v3-Large model](microsoft/deberta-v3-large) fine-tuned on [GPT Wiki intro](https://huggingface.co/datasets/aadityaubhat/GPT-wiki-intro) and [HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3) dataset.
8
+
9
+ We used a few tricks during training to optimize classification results.
10
 
11
  Fine-tuning was done for 1 epoch with 8:2 train/validation split. Recorded a validation accuracy of 99% for both GPT Wiki intro and HC3 after the 1st epoch.
12