Downloads · 30 days
34
0% of all-time downloads
bert-base-multilingual-cased-sentence
DeepPavlov/bert-base-multilingual-cased-sentence
bert-base-multilingual-cased-sentence is a feature extraction model from DeepPavlov. Use it when you need embeddings to search or compare text. It is set up for transformers.
Sentence Multilingual BERT \(101 languages, cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters\) is a representation‑based sentence encoder for 101 languages of Multilingual BERT. It is initialized with Multilingu…
All-time downloads
268K
Public
Repo size
2.8 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin711 MB · 50%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- May 18, 2021
- SHA
- 403febdd
Spaces
Model card
From the Hugging Face model README
bert-base-multilingual-cased-sentence
Sentence Multilingual BERT (101 languages, cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters) is a representation‑based sentence encoder for 101 languages of Multilingual BERT. It is initialized with Multilingual BERT and then fine‑tuned on english MultiNLI[1] and on dev set of multilingual XNLI[2]. Sentence representations are mean pooled token embeddings in the same manner as in Sentence‑BERT[3].
[1]: Williams A., Nangia N. & Bowman S. (2017) A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. arXiv preprint arXiv:1704.05426
[2]: Williams A., Bowman S. (2018) XNLI: Evaluating Cross-lingual Sentence Representations. arXiv preprint arXiv:1809.05053
[3]: N. Reimers, I. Gurevych (2019) Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv preprint arXiv:1908.10084
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- Languages
- multilingual
- Created
- Mar 2, 2022
- Updated
- May 18, 2021