cnmoro/portuguese-nomic-embed-text-v2-moe

pipeline_tag: sentence-similarity language: pt license: unknown tags:

• —passage-retrieval
• —sentence-similarity
• —pruned libraryname: sentence-transformers basemodel: nomic-ai/nomic-embed-text-v2-moe basemodelrelation: quantized ---

🇵🇹 portuguese-nomic-embed-text-v2-moe

This model is a 34.5% smaller version of nomic-ai/nomic-embed-text-v2-moe for the Portuguese language, created using (a modded version of) the mtem-pruner space.

This pruned model should perform similarly to the original model for Portuguese language tasks with a much smaller memory footprint. However, it may not perform well for other languages present in the original multilingual model as tokens not commonly used in Portuguese were removed from the original multilingual model's vocabulary.

[image]

Usage

You can use this model with the Transformers library:

from transformers import AutoModel, AutoTokenizer

model_name = "cnmoro/portuguese-nomic-embed-text-v2-moe"
model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_fast=True)

Or with the sentence-transformers library:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("cnmoro/portuguese-nomic-embed-text-v2-moe")

Credits: cc @antoinelouis