Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -13,12 +13,12 @@ base_model:
|
|
| 13 |
|
| 14 |
## Model Description
|
| 15 |
|
|
|
|
|
|
|
| 16 |
The **AI Detect Model** is a binary classification model designed to determine whether a given text is AI-generated (label=1) or written by a human (label=0). This model plays a crucial role in providing AI detection rewards, helping to prevent reward hacking during Reinforcement Learning with Cycle Consistency (RLCC). For more details, please refer to [our paper](https://tongyi.aliyun.com/qianwen/?sessionId=ea3bbcf36a2346a0a7819b06fcb36a1c#).
|
| 17 |
|
| 18 |
This model is built upon the [Longformer](https://huggingface.co/allenai/longformer-base-4096) architecture and trained using our proprietary [LMSYS-USP](https://huggingface.co/datasets/wangkevin02/LMSYS-USP) dataset. Specifically, in a dialogue context, texts generated by the assistant are labeled as AI-generated (label=1), while user-generated texts are assigned the opposite label (label=0).
|
| 19 |
|
| 20 |
-
If you are interested in exploring the source code and additional resources, feel free to visit our GitHub repository:https://github.com/wangkevin02/USP
|
| 21 |
-
|
| 22 |
> *Note*: Our model is subject to the following constraints:
|
| 23 |
>
|
| 24 |
> 1. **Maximum Context Length**: Supports up to **4,096 tokens**. Exceeding this may degrade performance; keep inputs within this limit for best results.
|
|
|
|
| 13 |
|
| 14 |
## Model Description
|
| 15 |
|
| 16 |
+
> **GitHub repository** for exploring the source code and additional resources:https://github.com/wangkevin02/USP
|
| 17 |
+
|
| 18 |
The **AI Detect Model** is a binary classification model designed to determine whether a given text is AI-generated (label=1) or written by a human (label=0). This model plays a crucial role in providing AI detection rewards, helping to prevent reward hacking during Reinforcement Learning with Cycle Consistency (RLCC). For more details, please refer to [our paper](https://tongyi.aliyun.com/qianwen/?sessionId=ea3bbcf36a2346a0a7819b06fcb36a1c#).
|
| 19 |
|
| 20 |
This model is built upon the [Longformer](https://huggingface.co/allenai/longformer-base-4096) architecture and trained using our proprietary [LMSYS-USP](https://huggingface.co/datasets/wangkevin02/LMSYS-USP) dataset. Specifically, in a dialogue context, texts generated by the assistant are labeled as AI-generated (label=1), while user-generated texts are assigned the opposite label (label=0).
|
| 21 |
|
|
|
|
|
|
|
| 22 |
> *Note*: Our model is subject to the following constraints:
|
| 23 |
>
|
| 24 |
> 1. **Maximum Context Length**: Supports up to **4,096 tokens**. Exceeding this may degrade performance; keep inputs within this limit for best results.
|