Update README.md

README.md

@@ -1,3 +1,50 @@
 ---
-license: apache-2.0
+{}
 ---
+
+<br>
+
+# RADAR Model Card
+
+## Model Details
+
+RADAR-Vicuna-7B is an AI-text detector trained via adversrial learning between the detector and a paraphraser on human-text corpus([OpenWebText](https://huggingface.co/datasets/Skylion007/openwebtext)) and ai-text corpus generated 
+from [OpenWebText](https://huggingface.co/datasets/Skylion007/openwebtext)
+
+- **Developed by:** [TrustSafeAI](https://huggingface.co/TrustSafeAI)
+- **Model type:** An encoder-only language model based on the transformer architecture.
+- **License:** Non-commercial license
+- **Trained from model:** [RoBERTa](https://arxiv.org/abs/1907.11692).
+
+### Model Sources
+
+- **Project Page:** https://radar.vizhub.ai/
+- **Paper:** https://arxiv.org/abs/2307.03838
+- **IBM Blog Post:** https://research.ibm.com/blog/AI-forensics-attribution
+
+## Uses
+Users could use this detector to assist them in detecting text generated by large language models.
+Please be noted that this detector is trained on ai-text generated by Vicuna-7B-v1.1. As the model only supports [non-commercial use](https://huggingface.co/lmsys/vicuna-7b-v1.1#model-details).
+So the intended users are not allowed to involve this detector into commercial activities.
+
+## Get Started with the Model
+Please refer the following google colab demo to see how to locally run the downloaded model or use our API service hosted on Huggingface Space.
+- Google Colab Demo: https://colab.research.google.com/drive/1XmqDFsSpLJ67EGXUl9MpapeJ-XozRRpq#scrollTo=w8s2p5lwkShg 
+- Huggingface API Documentation: https://trustsafeai-radar-ai-text-detector.hf.space/?view=api 
+
+## Training Pipeline
+
+We propose adversarial learning between a paraphraser and our detector. The paraphraser's goal is to make the AI-generated text more like human-writen and the detector's goal is to 
+promote it's ability to distinguish the human-text and ai-text.
+
+- **(Step 1) Training Data preparation**: Before training, we use Vicuna-7B to generate AI-text by performing text-completion based on the prefix span of human-text in [OpenWebText](https://huggingface.co/datasets/Skylion007/openwebtext).
+
+- **(Step 2) Update the paraphraser** During training, the paraphraser will do paraphrasing on the AI-text generated in **Step 1**. And then colect the reward returned by the detector to update the parphraser using Proxy Proximal Optimization loss.
+
+- **(Step 3) Update the detector** The detector is optimized using the logistic loss on the human-text,ai-text and paraphrased ai-text.
+
+See more details in the Section 3 and 4 of this [paper](https://arxiv.org/pdf/2307.03838.pdf).
+
+## Ethical Considerations
+we suggest users use our tool to assist with identifying AI-written content at scale and with discretion. If the detection result is to be used as evidence, further validation steps 
+are necessary as RADAR cannot always make correct predictions.