Update README.md

README.md

@@ -26,10 +26,10 @@ OpenFlamingo-9B is intended to be used **for academic research purposes only.**
 ### Bias, Risks, and Limitations
 This model may generate inaccurate or offensive outputs, reflecting biases in its training data and pretrained priors. 
 
-In an effort to mitigate current potential biases and harms, we have deployed a [content filter]() on model outputs in the OpenFlamingo demo. We continue to red-team the model to understand and improve its safety.
+In an effort to mitigate current potential biases and harms, we have deployed a content filter on model outputs in the OpenFlamingo demo. We continue to red-team the model to understand and improve its safety.
 
 ## Evaluation
-We've evaluated this checkpoint on the validation sets for two vision-language tasks: COCO captioning and VQAv2. Results are displayed below.
+We've evaluated this checkpoint and report validation performance for two vision-language tasks: COCO captioning and VQAv2. Results are displayed below.
 
 **COCO (CIDEr)**