Update README.md

README.md

@@ -29,6 +29,7 @@ language:
 - **Language(s) (NLP):** Mainly English
 - **License:** TII Falcon-Mamba License 2.0
 
+<br>
 
 # Usage
 
@@ -185,6 +186,8 @@ Also, we applied *BatchScaling* during the rampup — rescaling learning rate \\
 
 The model training took roughly two months. 
 
+<br>
+
 # Evaluation
 
 ## Benchmarks
@@ -235,6 +238,7 @@ pip install "causal-conv1d>=1.4.0" mamba-ssm
 Refer to our technical report for more details about performance evaluation.
 
 
+<br>
 
 # Technical Specifications 
 
@@ -262,6 +266,8 @@ Falcon-Mamba-7B was trained on AWS SageMaker, using on average 256 H100 80GB GPU
 
 Falcon-Mamba-7B was trained on an internal distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO, high-performance Triton kernels.
 
+<br>
+
 # Citation
 
 *Paper coming soon* 😊.