Text Classification
Transformers.js
ONNX
GLiNER2
English
deberta-v2
feature-extraction
webgpu
typed-decisions
open-jev
system-one
Instructions to use onnx-community/GLiNER2.5-Decide-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/GLiNER2.5-Decide-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-classification', 'onnx-community/GLiNER2.5-Decide-ONNX'); - GLiNER2
How to use onnx-community/GLiNER2.5-Decide-ONNX with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("onnx-community/GLiNER2.5-Decide-ONNX") # Extract entities text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday." result = extractor.extract_entities(text, ["company", "person", "product", "location"]) print(result) - Notebooks
- Google Colab
- Kaggle
File size: 1,505 Bytes
2a9b872 | 1 | [["My payouts have failed three times this week and nobody replied to my emails.", [["team", ["payments", "account", "other"], null], ["urgent", ["yes", "no"], null]]], ["Hi, I was charged twice for my Pro subscription this month, please fix.", [["Which team should handle this?", ["billing team", "technical support", "sales"], {"billing team": "charges, refunds, invoices", "technical support": "bugs, outages", "sales": "pricing, upgrades"}], ["Is the customer angry?", ["yes", "no"], null]]], ["The export button crashes in Safari but works in Chrome. Not blocking, we told users to switch browsers.", [["How severe is this bug?", ["cosmetic", "degraded but there is a workaround", "blocking"], null], ["Is the bug browser-specific?", ["no", "yes"], null], ["Should this be escalated?", ["no", "yes"], null]]], ["URGENT: production database is down, all customers affected, CEO is asking for updates every 5 minutes", [["priority", ["low", "medium", "high", "critical"], null], ["Is this a security incident?", ["no", "yes"], null]]], ["Thanks so much for the quick fix yesterday, everything works great now!", [["sentiment", ["negative", "neutral", "positive"], null], ["Does the customer need a reply?", ["no", "yes"], null]]], ["Can you send me the invoice for March? Also my login stopped working on the mobile app.", [["Which team should handle this?", ["billing", "technical support", "sales"], null], ["How many separate requests are in this message?", ["one", "two", "three or more"], null]]]] |