Downloads · 30 days
49
4% of all-time downloads
fasttext-classification
paulhindemith/fasttext-classification
fasttext-classification is a zero-shot classification model from paulhindemith. Use it when you need labels you did not train the model on. It is set up for transformers. The card lists the license as cc-by-sa-3.0.
All-time downloads
1.2K
Public
Repo size
2.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.4 GB · 99%
At a glance
- Task
- Zero-Shot Classification
- Library
- transformers
- License
- cc-by-sa-3.0
- Model type
- fasttext_classification
- Access
- Public
- Created
- Nov 6, 2022
- Updated
- Nov 20, 2022
- SHA
- 46f1d8c8
Try a prompt
Model card
From the Hugging Face model README
fasttext-classification
This model is experimental.
fastText word vector base classification
Usage
Google Colaboratory Example
! apt install aptitude swig > /dev/null
! aptitude install mecab libmecab-dev mecab-ipadic-utf8 git make curl xz-utils file -y > /dev/null
! pip install transformers torch mecab-python3 torchtyping > /dev/null
! ln -s /etc/mecabrc /usr/local/etc/mecabrc
from transformers import pipeline
p = pipeline("zero-shot-classification", "paulhindemith/fasttext-classification", revision="2022.11.13", trust_remote_code=True)
p("海賊王におれはなる", candidate_labels=["海","山","陸"], hypothesis_template="{}", multi_label=True)
License
This model utilizes the folllowing pretrained vectors.
Name: fastText
Credit: https://fasttext.cc/
License: Creative Commons Attribution-Share-Alike License 3.0
Link: https://dl.fbaipublicfiles.com/fasttext/vectors-wiki/wiki.ja.vec
- Task
- Zero-Shot Classification
- Library
- transformers
- Type
- fasttext_classification
- License
- cc-by-sa-3.0
- Languages
- ja
- Created
- Nov 6, 2022
- Updated
- Nov 20, 2022