metadata
license: apache-2.0
datasets:
- cnmoro/AllTripletsMsMarco-PTBR
- Tevatron/msmarco-passage-corpus
language:
- en
- pt
library_name: model2vec
base_model:
- nomic-ai/nomic-embed-text-v2-moe
pipeline_tag: feature-extraction
This Model2Vec model was created by using Tokenlearn, with nomic-embed-text-v2-moe as a base, trained on around 3.5M passages (english and portuguese).
I have yet to run any benchmarks on it, but it easily outperforms potion-multilingual-128M on my custom-portuguese-testing-workload-thing.
The output dimension is 512.
Usage
Load this model using the from_pretrained method:
from model2vec import StaticModel
# Load a pretrained Model2Vec model
model = StaticModel.from_pretrained("cnmoro/static-nomic-eng-ptbr")
# Compute text embeddings
embeddings = model.encode(["Example sentence"])