[Model]: Add new model Snowflake's Arctic-embed v2.0

[wannaphong]

Which model would you like to support?

Model:

• Snowflake/snowflake-arctic-embed-l-v2.0
• Snowflake/snowflake-arctic-embed-m-v2.0

What are the main advantages of this model?

multilingual work

[joein]

These models could be added to fastembed v0.6.0 in runtime via .add_custom_model interface

An example of usage of this interface:

from fastembed import TextEmbedding
from fastembed.common.model_description import PoolingType, ModelSource

TextEmbedding.add_custom_model(
    model="intfloat/multilingual-e5-small",
    pooling=PoolingType.MEAN,
    normalization=True,
    sources=ModelSource(hf="intfloat/multilingual-e5-small"),  # can be used with an `url` to load files from a private storage
    dim=384,
    model_file="onnx/model.onnx",  # can be used to load an already supported model with another optimization or quantization, e.g. onnx/model_O4.onnx
)
model = TextEmbedding(model_name="intfloat/multilingual-e5-small")
embeddings = list(model.embed(documents))

[rplescia]

Which model would you like to support?

Model:

• Snowflake/snowflake-arctic-embed-l-v2.0
• Snowflake/snowflake-arctic-embed-m-v2.0

What are the main advantages of this model?

multilingual work

Yes please! These 2 models get my vote