Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[D] Transformer Libraries/Benchmarks? (alien.top)

submitted 11 months ago by Acciorocketships@alien.top to c/machinelearning@academy.garden

1 comments fedilink hide all child comments

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.

you are viewing a single comment's thread
view the rest of the comments

[–] KingsmanVince@alien.top 1 points 11 months ago

You can check out HuggingFace transformers, xformers, Lucidrains implementations. For benchmarking, just test on GLUE.