Downloads · 30 days
26
2% of all-time downloads
lsg-ner-vietnamese-electra-base-1024
nguyendangsonlam/lsg-ner-vietnamese-electra-base-1024
lsg-ner-vietnamese-electra-base-1024 is a token classification model from nguyendangsonlam. Use it when you need labels on individual words, such as names. It is set up for transformers.
A LSG version with extended input length based on NlpHUST/ner-vietnamese-electra-base and LSG Attention.\ Remember to add trustremotecode=True option while loading the model.
All-time downloads
1.4K
Public
Repo size
1.1 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin537 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- electra
- Access
- Public
- Created
- Jan 4, 2023
- Updated
- Jan 4, 2023
- SHA
- 7e446c81
Try a prompt
Model card
From the Hugging Face model README
LSG ner vietnamese electra base model with max input length of 1024
A LSG version with extended input length based on NlpHUST/ner-vietnamese-electra-base and LSG Attention.
Remember to add trust_remote_code=True option while loading the model.
Usage
Fill mask example:
from transformers import AutoModelForTokenClassification, AutoTokenizer, pipeline
model = AutoModelForTokenClassification.from_pretrained("nguyendangsonlam/lsg-ner-vietnamese-electra-base-1024", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("nguyendangsonlam/lsg-ner-vietnamese-electra-base-1024")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Chiều 3/1, Đoàn công tác của Báo Nhân Dân do đồng chí Lê Quốc Minh, Ủy viên Trung ương Đảng, Tổng Biên tập Báo Nhân Dân, Phó Trưởng Ban Tuyên giáo Trung ương, Chủ tịch Hội Nhà báo Việt Nam làm Trưởng đoàn đã có buổi làm việc với lãnh đạo tỉnh Tuyên Quang."
ner_results = nlp(example)
print(ner_results)
- Task
- Token Classification
- Library
- transformers
- Type
- electra
- Languages
- vi
- Created
- Jan 4, 2023
- Updated
- Jan 4, 2023