Update README.md

README.md

@@ -2,17 +2,16 @@
 
 Felix-8B is a state-of-the-art language model developed by Ontocord.ai, specializing in safety and truthful question answering. This model has achieved one of the highest scores on the TruthfulQA benchmark compared to models of its size, showcasing its exceptional performance in providing accurate and reliable responses.
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/630430583926de1f7ec62c6b/zKoEI-B21KnmeRWvKzrx1.png)
+
 ## Model Description
 
 Felix-8B is an 8 billion parameter language model trained using Ontocord.ai's proprietary auto-purpleteaming technique. The model has been fine-tuned and optimized using synthetic data, ensuring its robustness and ability to handle a wide range of tasks while maintaining a strong focus on safety and truthfulness.
 
-## Training Data
-
-Felix-8B has been trained on a diverse corpus of high-quality text data, including books, articles, and web pages. The model has also undergone fine-tuning using synthetic data generated through Ontocord.ai's auto-purpleteaming technique, which enhances its performance on safety-critical tasks and improves its ability to provide truthful responses.
 
 ## Evaluation
 
-Felix-8B has been extensively evaluated on various benchmarks, including the TruthfulQA benchmark, where it has achieved one of the highest scores among models of its size. The model has also demonstrated strong performance on other standard NLP benchmarks, such as GLUE, SuperGLUE, and SQuAD.
+Felix-8B has been extensively evaluated on various benchmarks, including the TruthfulQA benchmark, where it has achieved one of the highest scores among models of its size.
 
 ## Limitations and Biases