Zero-Shot Classification
Core ML
GLiNER
GLiNER2
English
coremltools
deberta-v3
apple-silicon
fp16
multifunction
Instructions to use augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512 with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512") text = "Cristiano Ronaldo dos Santos Aveiro was born on 5 February 1985 in Funchal, Madeira, Portugal." labels = ["person", "date", "location"] entities = model.predict_entities(text, labels) for entity in entities: print(entity["text"], "=>", entity["label"]) - GLiNER2
How to use augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512 with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512") # 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 pyproject.toml from augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512: direct link, hf CLI and curl.
- Browser
- Download file 1.01 kB
-
https://huggingface.co/augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512/resolve/cb96101a108e3e756eb581e6be780eac3a93b2f2/pyproject.toml
- Command line
-
hf download hf://augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512@cb96101a108e3e756eb581e6be780eac3a93b2f2/pyproject.toml
-
curl -L -o pyproject.toml https://huggingface.co/augustoFranke/GLiNER2.5-Decide-CoreML-FP16-MultiFn-L64-512/resolve/cb96101a108e3e756eb581e6be780eac3a93b2f2/pyproject.toml
1.01 kB
| [project] | |
| name = "gliner-decide-coreml" | |
| version = "0.1.0" | |
| description = "GLiNER2.5-Decide as one Core ML multifunction package (64/128/256/512-token buckets) with automatic bucket routing, tuned for Apple Silicon GPUs." | |
| readme = "README.md" | |
| license = "Apache-2.0" | |
| requires-python = ">=3.10,<3.13" | |
| # Pinned to the versions the Core ML buckets were converted and verified with. | |
| # torch/transformers are needed only because GLiNER2's schema preprocessing imports them. | |
| dependencies = [ | |
| "coremltools==9.0", | |
| "gliner2[local]==2.0.0", | |
| "huggingface-hub>=0.34,<1", | |
| "numpy<2.3", | |
| "sentencepiece>=0.2,<0.3", | |
| "torch==2.7.0", | |
| "transformers==4.57.6", | |
| ] | |
| [dependency-groups] | |
| dev = [ | |
| "pytest>=8", | |
| ] | |
| [build-system] | |
| requires = ["hatchling"] | |
| build-backend = "hatchling.build" | |
| [tool.hatch.build.targets.wheel] | |
| packages = ["src/gliner_decide_coreml"] | |
| [tool.pytest.ini_options] | |
| testpaths = ["tests"] | |
| filterwarnings = ["ignore::DeprecationWarning", "ignore::UserWarning", "ignore::FutureWarning"] | |