Update README.md

README.md

@@ -8,10 +8,9 @@ inference: false
 
 # Monarch Mixer-BERT
 
-The 80M checkpoint for M2-BERT-base from the paper [Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture](https://arxiv.org/abs/2310.12109).
-This model has been pretrained with sequence length 2048, and it has been fine-tuned for long-context retrieval.
+An 80M checkpoint of M2-BERT, pretrained with sequence length 2048, and it has been fine-tuned for long-context retrieval.
 
-Check out our [blog post]() for more on how we trained this model for long sequence.
+Check out the paper [Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture](https://arxiv.org/abs/2310.12109) and our [blog post]() on retrieval for more on how we trained this model for long sequence.
 
 This model was trained by Jon Saad-Falcon, Dan Fu, and Simran Arora.