sup-SimCSE-VietNamese-phobert

About

What sup-SimCSE-VietNamese-phobert is

Table of contents 1. Introduction 2. Pretrain model 3. Using SimeCSEVietnamese with sentences-transformers - Installation - Example usage 4. Using SimeCSEVietnamese with transformers - Installation - Example usage <a name="introduction"</a SimeCSEVietnamese: Simple Contrastive Learning of Sentence Embeddings with Vietnamese Pre-trained SimeCSEVietnamese models are the state-of-the-art of Sentence Embeddings with Vietnamese : - SimeCSEVietnamese pre-training approach is based on SimCSE which optimizes the SimeCSEVietnamese pre-training procedure for more robust performance. - SimeCSEVietnamese encode input sentences using a pre-trained language model such as PhoBert - SimeCSEVietnamese works with both unlabeled and labeled data. Pre-trained models <a name="models"</a Model | #params | Arch. VoVanPhuc/sup-SimCSE-VietNamese-phobert-base | 135M | base VoVanPhuc/unsup-SimCSE-VietNamese-phobert-base | 135M | base <a name="sentences-transformers"</a Using SimeCSEVietnamese with sentences-transformers Installation <a name="install1"</a - Install sentence-transformers: - pip install -U sentence-transformers - Install pyvi to word segment: - pip install pyvi Example usage <a name="usage1"</a <a name="sentences-transformers"</a Using SimeCSEVietnamese with transformers Installation <a name="install2"</a - Install transformers: - pip install -U transformers - Install pyvi to word segment: - pip install pyvi Example usage <a name="usage2"</a Quick Start Open In Colab Citation @article{gao2021simcse, title={{SimCSE}: Simple Contrastive Learning of Sentence Embeddings}, author={Gao, Tianyu and Yao, Xingcheng and Chen, Danqi}, journal={arXiv preprint arXiv:2104.08821}, year={2021} } @inproceedings{phobert, title = {{PhoBERT: Pre-trained language models for Vietnamese}}, author = {Dat Quoc Nguyen and Anh Tuan Nguyen}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, year = {2020}, pages = {1037--1042} }

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How embedding models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys sup-simcse-vietnamese-phobert for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (sup-simcse-vietnamese-phobert below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"sup-simcse-vietnamese-phobert","input":"text to embed"}'

Details

Languages, data & research

Papers

Licence

Commercial licence needed

Sources

Weights & code

Explore

More embedding models