Deprecated. This model is superseded and is kept only so existing installs keep resolving. It was trained before the OVOS intent corpus was rebuilt from a pinned, reproducible pipeline, and its label set no longer matches what the OVOS m2v pipeline registers.
Use OpenVoiceOS/ovos-m2v-intents-multilingual instead, or OpenVoiceOS/ovos-m2v-intents-en on an English-only device. Both ship a
labels.jsonbeside the weights.
This Model2Vec model is a fine-tuned version of the unknown Model2Vec model. It also includes a classifier head on top.
Install model2vec using pip:
pip install model2vec[inference]
Load this model using the from_pretrained method:
from model2vec.inference import StaticModelPipeline
# Load a pretrained Model2Vec model
model = StaticModelPipeline.from_pretrained("ovos-intents-es-b32e30-n1d128-m2v-256-roberta-large-bne")
# Predict labels
predicted = model.predict(["Example sentence"])
Model2Vec was developed by the Minish Lab team consisting of Stephan Tulkens and Thomas van Dongen.
Please cite the Model2Vec repository if you use this model in your work.
@article{minishlab2024model2vec,
author = {Tulkens, Stephan and {van Dongen}, Thomas},
title = {Model2Vec: Fast State-of-the-Art Static Embeddings},
year = {2024},
url = {https://github.com/MinishLab/model2vec}
}