Instructions to use FluidInference/gliner2-5-base-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER2
How to use FluidInference/gliner2-5-base-coreml with GLiNER2:
from gliner2 import GLiNER2 model = GLiNER2.from_pretrained("FluidInference/gliner2-5-base-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 reports/extraction-validation.json from FluidInference/gliner2-5-base-coreml: direct link, hf CLI and curl.
- Browser
- Download file 2.46 kB
-
https://huggingface.co/FluidInference/gliner2-5-base-coreml/resolve/main/reports/extraction-validation.json
- Command line
-
hf download hf://FluidInference/gliner2-5-base-coreml/reports/extraction-validation.json
-
curl -L -o extraction-validation.json https://huggingface.co/FluidInference/gliner2-5-base-coreml/resolve/main/reports/extraction-validation.json
2.46 kB
| { | |
| "purpose": "selected local Core ML extraction parity and latency, not a Decision Index score", | |
| "source_model": "fastino/gliner2.5-base-v1", | |
| "source_revision": "1a8bc24e00dc7300b9017c81d63e3dcdabb26596", | |
| "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": 11, | |
| "fixture_count": 11, | |
| "failed_cases": [], | |
| "maximum_confidence_error": 1.1324882507324219e-06 | |
| }, | |
| "fp16": { | |
| "matched_structures": 11, | |
| "fixture_count": 11, | |
| "failed_cases": [], | |
| "maximum_confidence_error": 0.16530340909957886 | |
| } | |
| }, | |
| "latency": { | |
| "fp16_all": { | |
| "p50_ms": 8.981791470432654, | |
| "p95_ms": 16.104084032122046, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| }, | |
| "fp16_cpu_and_gpu": { | |
| "p50_ms": 8.275083499029279, | |
| "p95_ms": 13.875250006094575, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| }, | |
| "fp16_cpu_and_neural_engine": { | |
| "p50_ms": 10.255208006128669, | |
| "p95_ms": 14.293458021711558, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| }, | |
| "fp16_cpu_only": { | |
| "p50_ms": 21.39054099097848, | |
| "p95_ms": 33.066082978621125, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| }, | |
| "fp32_all": { | |
| "p50_ms": 9.933604509569705, | |
| "p95_ms": 10.4843340232037, | |
| "warmup": 20, | |
| "iterations": 200, | |
| "shape": "L128/W64/Q8/C192" | |
| } | |
| }, | |
| "feature_compute_plan": { | |
| "fp16-cpu_and_neural_engine": { | |
| "cpu_percent": 46.87, | |
| "gpu_percent": 0.0, | |
| "ane_percent": 53.13 | |
| } | |
| }, | |
| "compression": { | |
| "attempt": "LUT8 per-tensor k-means on FP16 feature package using scikit-learn 1.5.1", | |
| "source_bytes": 390998448, | |
| "compressed_bytes": 196248206, | |
| "matched_structures": 10, | |
| "fixture_count": 11, | |
| "failed_cases": [ | |
| "record_latent" | |
| ], | |
| "release": false | |
| }, | |
| "published_extraction_precisions": [ | |
| "fp16", | |
| "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" | |
| ] | |
| } | |