Update README.md
Browse files
README.md
CHANGED
@@ -12,12 +12,15 @@ tags:
|
|
12 |
|
13 |
This model is trained on `question-answer` pairs of **the filtered full-text** from [Hello-SimpleAI/HC3-Chinese](https://huggingface.co/datasets/Hello-SimpleAI/HC3-Chinese).
|
14 |
|
|
|
|
|
15 |
|
16 |
The base checkpoint is [hfl/chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext).
|
17 |
We train it with all [Hello-SimpleAI/HC3-Chinese](https://huggingface.co/datasets/Hello-SimpleAI/HC3-Chinese) data (without held-out) for 2 epochs.
|
18 |
|
19 |
( 2-epoch is consistent with the experiments in [our paper](https://arxiv.org/abs/2301.07597).)
|
20 |
|
|
|
21 |
## Citation
|
22 |
|
23 |
Checkout this papaer [arxiv: 2301.07597](https://arxiv.org/abs/2301.07597)
|
|
|
12 |
|
13 |
This model is trained on `question-answer` pairs of **the filtered full-text** from [Hello-SimpleAI/HC3-Chinese](https://huggingface.co/datasets/Hello-SimpleAI/HC3-Chinese).
|
14 |
|
15 |
+
More details ref to Gtihub project [Hello-SimpleAI/chatgpt-comparison-detection](https://github.com/Hello-SimpleAI/chatgpt-comparison-detection).
|
16 |
+
|
17 |
|
18 |
The base checkpoint is [hfl/chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext).
|
19 |
We train it with all [Hello-SimpleAI/HC3-Chinese](https://huggingface.co/datasets/Hello-SimpleAI/HC3-Chinese) data (without held-out) for 2 epochs.
|
20 |
|
21 |
( 2-epoch is consistent with the experiments in [our paper](https://arxiv.org/abs/2301.07597).)
|
22 |
|
23 |
+
|
24 |
## Citation
|
25 |
|
26 |
Checkout this papaer [arxiv: 2301.07597](https://arxiv.org/abs/2301.07597)
|