Transformers
Safetensors
GLiNER2
multilingual
English
Text classification
Intent classification
Sentiment Analysis
Topic classification
Named Entity Recognition
decision-model
schema-extraction
Instructions to use fastino/GLiNER2.5-multi-Decide with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fastino/GLiNER2.5-multi-Decide with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import Gliner2ForSchemaExtraction model = Gliner2ForSchemaExtraction.from_pretrained("fastino/GLiNER2.5-multi-Decide", device_map="auto") - GLiNER2
How to use fastino/GLiNER2.5-multi-Decide with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("fastino/GLiNER2.5-multi-Decide") # 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
Install with the local extra: pip install "gliner2[local]"
#8
by kzfastino - opened
Plain pip install gliner2 is torch-free, so the AutoExtractor example on the next lines fails without the local extra (see the install section of the GLiNER2 README).
This is the install-line change from #3, rebased on current main so it changes nothing else. #3 also edits metadata and banner links that were changed on main more recently, which is why it is split out.
kzfastino changed pull request status to merged