Sentence Similarity
sentence-transformers
Safetensors
modernbert
feature-extraction
dense
Generated from Trainer
dataset_size:5647936
loss:EmbedDistillLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use yjoonjang/MIMO-mmBERT-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use yjoonjang/MIMO-mmBERT-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("yjoonjang/MIMO-mmBERT-base") sentences = [ "Quiero dar las gracias -quiero decirlo correctamente- a la Comisión dimitida que se encuentra todavía en funciones, porque no fue una labor sencilla.", "They say you killed Joffrey.", "es", "I should like to thank the Commission which - I want to get this right - has resigned, but which is still in office. It has not been an easy time." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- daf46a52874fb9b6191b9ae46a0f471904405b611f8e1d580f76c7424d343f89
- Size of remote file:
- 34.4 MB
- SHA256:
- 17f7d8b9518c403d7429ad9eeeabb6eed49c8d3311de8ef4ed5ad811381a2ced
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.