Instructions to use FluidInference/gliner2-5-small-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER2
How to use FluidInference/gliner2-5-small-coreml with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("FluidInference/gliner2-5-small-coreml") # 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
|
Download CONFIG_PROVENANCE.md from FluidInference/gliner2-5-small-coreml: direct link, hf CLI and curl.
- Browser
- Download file 629 Bytes
-
https://huggingface.co/FluidInference/gliner2-5-small-coreml/resolve/main/CONFIG_PROVENANCE.md
- Command line
-
hf download hf://FluidInference/gliner2-5-small-coreml/CONFIG_PROVENANCE.md
-
curl -L -o CONFIG_PROVENANCE.md https://huggingface.co/FluidInference/gliner2-5-small-coreml/resolve/main/CONFIG_PROVENANCE.md
629 Bytes
Root config provenance
The root config.json is an unmodified copy of the full upstream model config from fastino/gliner2.5-small-v1 at 7e6f537f10337497069276892a5ef435028252ce, path config.json.
SHA-256: 0b7d9e1401ceeb83e992ec66d2f93bff7e5646428f1b4706ec527cf88f53578a.
This file describes the source architecture. It does not make the Core ML package a standalone Transformers AutoModel checkpoint. Use the repository's Core ML runtime and its included tokenizer, decision heads, and calibration where applicable.