fix: Register MicroLlama Text Embedding

[keeeeenw]

Adding a model checklist

• I have filled out the ModelMeta object to the extent possible
• I have ensured that my model can be loaded using
  • mteb.get_model(model_name, revision) and
  • mteb.get_model_meta(model_name, revision)
• I have tested the implementation works on a representative set of tasks.

Testing results

>>> import mteb
>>> mteb.get_model_meta("keeeeenw/MicroLlama-text-embedding", "98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e")
ModelMeta(name='keeeeenw/MicroLlama-text-embedding', revision='98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e', release_date='2024-11-10', languages=['eng-Latn'], loader=None, n_parameters=272000000, memory_usage=None, max_tokens=2048.0, embed_dim=1024, license='apache-2.0', open_weights=True, public_training_data=None, public_training_code=None, framework=['Sentence Transformers', 'PyTorch'], reference='https://huggingface.co/keeeeenw/MicroLlama-text-embedding', similarity_fn_name='cosine', use_instructions=False, training_datasets=None, adapted_from=None, superseded_by=None)
>>> tasks = mteb.get_tasks(tasks=["Banking77Classification"])
... evaluation = mteb.MTEB(tasks=tasks)
... 
>>> model = mteb.get_model("keeeeenw/MicroLlama-text-embedding", "98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e")
Loader not specified for model keeeeenw/MicroLlama-text-embedding, loading using sentence transformers.
>>> evaluation.run(model)