feat: Support sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

[geetu040]

Issue

This PR resolves issue #89

The requested model, sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 has been included in the package by adding this configuration

    {
        "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
        "dim": 384,
        "description": "Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2",
        "size_in_GB": 0.46,
        "hf_sources": [
            "qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q"
        ],
        "compressed_url_sources": []
    },

Usage

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 can now be used with fastembed

from fastembed import TextEmbedding

# load the model
embedding_model = TextEmbedding(
	model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
)

embeddings = embedding_model.embed(
	# documents
	["hello world", "flag embedding"] * 100,

	# optional params
	batch_size=2,
	parallel=2
)

Changes

Following changes were made to add this model

• fastembed/fastembed/models.json: model configuration was added
• fastembed/fastembed/text/onnx_embedding.py: model configuration was added in variable supported_onnx_models
• fastembed/fastembed/docs/examples/Supported_Models.ipynb: This notebook was run to show the latest model included in the output
• fastembed/tests/test_onnx_embeddings.py and fastembed/tests/test_text_onnx_embeddings.py: New model was added in list with the output generated on hard-coded documents for test-cases

Tests

All test cases have been passed with the latest model included

[Anush008]

Great work @geetu040. Thank you.