fix: Select benchmarks CLI option

[isaac-chung]

Address #1250 point 2.

• Added test cases for a list of Benchmark objects passed into the task parameter
• Added command line option to select Benchmarks

The following can now run. 1) script

from sentence_transformers import SentenceTransformer
import mteb

model_name = "average_word_embeddings_komninos"
model = SentenceTransformer(model_name)
benchmark = mteb.get_benchmarks(names=["MTEB(eng)"])
evaluation = mteb.MTEB(tasks=benchmark)
results = evaluation.run(model)

and command line:

mteb run -m average_word_embeddings_komninos -b 'MTEB(eng)'

Checklist

• Run tests locally to make sure nothing is broken using make test.
• Run the formatter to format the code using make lint.

[KennethEnevoldsen]

only a few minor things.

[isaac-chung]

Thanks! 🚀 Enabling auto-merge.