Improve comparison performance

README.md

@@ -27,14 +27,14 @@ It only uses models where necessary, which improves speed and accuracy.
 | PDF | File type | Markdown                                                                                                                     | JSON                                                                                                   |
 |-----|-----------|------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------|
 | [Think Python](https://greenteapress.com/thinkpython/thinkpython.pdf) | Textbook | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/markdown/thinkpython/thinkpython.md)                 | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/json/thinkpython.json)         |
-| [Switch Transformers](https://arxiv.org/pdf/2101.03961.pdf) | arXiv paper | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/markdown/switch_transformers/switch_transformers.md) | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/json/switch_transformers.json) |
+| [Switch Transformers](https://arxiv.org/pdf/2101.03961.pdf) | arXiv paper | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/markdown/switch_transformers/switch_trans.md) | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/json/switch_trans.json) |
 | [Multi-column CNN](https://arxiv.org/pdf/1804.07821.pdf) | arXiv paper | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/markdown/multicolcnn/multicolcnn.md)                 | [View](/~https://github.com/VikParuchuri/marker/blob/master/data/examples/json/multicolcnn.json)         |
 
 ## Performance
 
 ![Benchmark overall](data/images/overall.png)
 
-The above results are with marker setup so it takes ~4GB of VRAM on an A6000.
+The above results are with marker setup so it takes ~7GB of VRAM on an A10.
 
 See [below](#benchmarks) for detailed speed and accuracy benchmarks, and instructions on how to run your own benchmarks.