Update README.md

README.md

@@ -10,12 +10,30 @@ language:
 
 [GitHub](https://github.com/RLHF-V/RLAIF-V)
 
-RLAIF-V is a novel framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. RLAIF-V maximally exploits the open-source feedback from two key perspectives, including high-quality feedback data and online feedback learning algorithm. 
+**RLAIF-V-7B** is a variant of LLaVA-v1.5-7B with greatly enhanced trustworthiness. The model is trained by a novel framework, **RLAIF-V**, that aligns MLLMs in a **fully open-source paradigm for super GPT-4V trustworthiness**. RLAIF-V maximally exploits the open-source feedback from two key perspectives, including **high-quality feedback data** and an **online feedback learning algorithm**. 
 
 
 ## Model Details
 
+### Key Features
+
+* 📈**Best trustworthiness enhancement on LLaVA-v1.5**: By learning from open-source AI feedback, specifically, the feedback from LLaVA-NeXT-34B, RLAIF-V-7B achieves the best trustworthiness improvement on LLaVA-v1.5 compared to other hallucination reduction methods.
+* 💪**Maintaining Well Performance on General Abilities**: On benchmarks tested with the general abilities (e.g. LLaVABench, MMStar), RLAIF-V-7B also exhibits good performance.
+
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/ypXZxb4HE-jDPJU9115bi.png" alt="fig1" width="90%"/>
+</p>
+
+### Examples
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/Hyu2Et5CQtDFmxaYHKdu-.png" alt="fig2-1" width="80%"/>
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/16mJpyH_-vnRfl8Ywfa6k.png" alt="fig2-1" width="80%"/>
+</p>
+
 ### Model Description
 - **Trained from model:** [llava-v1.5-7B](https://huggingface.co/liuhaotian/llava-v1.5-7b)
 - **Trained on data:** [RLAIF-V-Dataset](https://huggingface.co/datasets/HaoyeZhang/RLAIF-V-Dataset)
 
+## Usage
+Please look at [GitHub](https://github.com/RLHF-V/RLAIF-V) for more details about usage.