Update README.md

README.md

@@ -18,7 +18,21 @@ language:
 - **Point of Contact:seongyun@kaist.ac.kr**
 
 # TL; DR
-Janus 7B is a model trained using [Mistral-7B-v0.2](https://huggingface.co/mistral-community/Mistral-7B-v0.2) as its base model. Janus 7B has been trained on [Multifaceted Collection](), a preference dataset with 192k combinations of values that go beyond generic helpfulness and harmlessness, spanning 65k user instructions. Janus 7B not only excels at generating personalized responses on [Multifaceted Bench]() that cater to various human preferences but is also adept at producing responses that are generally preferred for being helpful and harmless.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6550c4f27bbfce1878f5f280/vrQl8D8FV3vqUJYbPgsiG.png)
+
+Janus is a model trained using [Mistral-7B-v0.2](https://huggingface.co/mistral-community/Mistral-7B-v0.2) as its base model. Janus has been trained on [Multifaceted Collection](), a preference dataset with 192k combinations of values that go beyond generic helpfulness and harmlessness, spanning 65k user instructions. Janus not only excels at generating personalized responses on [Multifaceted Bench]() that cater to various human preferences but is also adept at producing responses that are generally preferred for being helpful and harmless.
+
+# Model Details
+
+## Model Description
+
+- **Model type:** Language model
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Related Models:** [Janus-66k-7B]() [Janus-DPO-7B](), [Janus-ORPO-7B](), [Janus-RM-7B]()
+- **Resources for more information:**
+  - [Research paper]()
+  - [GitHub Repo](https://github.com/kaistAI/Janus)
 
 ### Training hyperparameters