Instructions to use FluidInference/gliner2-5-multi-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER2
How to use FluidInference/gliner2-5-multi-coreml with GLiNER2:
from gliner2 import GLiNER2 model = GLiNER2.from_pretrained("FluidInference/gliner2-5-multi-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
| { | |
| "purpose": "selected local Core ML extraction parity and latency, not a Decision Index score", | |
| "source_model": "fastino/gliner2.5-multi-v1", | |
| "source_revision": "a221b77a8baf4a613b8f8652661d41fa10a5641e", | |
| "runtime": { | |
| "coremltools": "9.0", | |
| "gliner2": "2.0.0", | |
| "mac": "M5 Pro, 24 GB, macOS 27.0" | |
| }, | |
| "bucket": "L128/W64/Q8/K8; candidate C192, explicit S64, relation R4/P256, records F8/C192/I1536", | |
| "fixtures": { | |
| "fp32": { | |
| "matched_structures": 15, | |
| "fixture_count": 15, | |
| "failed_cases": [], | |
| "maximum_confidence_error": 4.887580871582031e-06 | |
| }, | |
| "fp16": { | |
| "matched_structures": 14, | |
| "fixture_count": 15, | |
| "failed_cases": [ | |
| "record_latent" | |
| ], | |
| "maximum_confidence_error": 0.037593305110931396 | |
| } | |
| }, | |
| "latency": { | |
| "fp32_all": { | |
| "p50_ms": 10.563604475464672, | |
| "p95_ms": 12.338125030510128, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| }, | |
| "fp32_cpu_and_gpu": { | |
| "p50_ms": 10.022375005064532, | |
| "p95_ms": 10.64095797482878, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| }, | |
| "fp32_cpu_and_neural_engine": { | |
| "p50_ms": 36.07562501565553, | |
| "p95_ms": 52.11695801699534, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| }, | |
| "fp32_cpu_only": { | |
| "p50_ms": 36.11889548483305, | |
| "p95_ms": 62.56379099795595, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| } | |
| }, | |
| "feature_compute_plan": { | |
| "fp32-all": { | |
| "cpu_percent": 0.0, | |
| "gpu_percent": 100.0, | |
| "ane_percent": 0.0 | |
| }, | |
| "fp32-cpu_and_neural_engine": { | |
| "cpu_percent": 100.0, | |
| "gpu_percent": 0.0, | |
| "ane_percent": 0.0 | |
| } | |
| }, | |
| "compression": { | |
| "attempt": "LUT8 per-tensor k-means on FP32 feature package using scikit-learn 1.5.1", | |
| "result": "stopped after two minutes with zero graph operations processed and repeated k-means divide-by-zero/overflow warnings", | |
| "release": false | |
| }, | |
| "published_extraction_precisions": [ | |
| "fp32" | |
| ], | |
| "limitations": [ | |
| "fixed shape; requests over capacity fail", | |
| "small selected real-text fixtures only; no full Decision Index score", | |
| "current pinned source revision is not established as the historical evaluation checkpoint" | |
| ] | |
| } | |