cnmoro/custom-model2vec-tokenlearn-medium

1---2library_name: model2vec3license: mit4model_name: cnmoro/custom-model2vec-tokenlearn-medium5tags:6- embeddings7- static-embeddings8- sentence-transformers9language:10- pt11- en12---13A custom model2vec model, trained using a modified version of the [tokenlearn](https://github.com/MinishLab/tokenlearn) library.14 15Base model is nomic-ai/nomic-embed-text-v2-moe.16 17The output dimension is 256, and the vocabulary size is 249.99918 19The training process used a mix of English (10%) and Portuguese (90%) texts.20 21```python22from model2vec import StaticModel23 24# Load a pretrained Sentence Transformer model25model = StaticModel.from_pretrained("cnmoro/custom-model2vec-tokenlearn-medium")26 27# Compute text embeddings28embeddings = model.encode(["Example sentence"])29```