For those of you who work with Transformers, are there any good pytorch libraries or performance benchmarks out there? Note that I am not looking for LLMs, I would just like implementations of the standard Transformer and various newer methods such as the Linear Transformer, Performer, Linformer, Reformer, etc. Ideally, I would like a library that also includes benchmarks, where various models can be compared in performance on simple to complex tasks. I would like to get into research in this space, but I don't know where to start.