Instructions to use fastino/GLiNER2.5-Decide with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fastino/GLiNER2.5-Decide with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="fastino/GLiNER2.5-Decide")# pip install -U transformers accelerate # Load model directly from transformers import Gliner2ForSchemaExtraction model = Gliner2ForSchemaExtraction.from_pretrained("fastino/GLiNER2.5-Decide", device_map="auto") - GLiNER2
How to use fastino/GLiNER2.5-Decide with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("fastino/GLiNER2.5-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) - Inference
- Notebooks
- Google Colab
- Kaggle
Add safeagents judge bench results
Hi! This adds fastino/GLiNER2.5-Decide's results on the safeagents judge bench, a benchmark of real agent tool calls that safeagents' scanner flags as suspicious, each labelled block or allow and with a kind of misuse (reward hacking, harness introspection, credential misuse, ...).
On the 562 test calls: balanced accuracy 0.577, AUROC 0.523, false-block rate 0.0, category macro F1 0.344. Run zero-shot, one System One request per call, on Apple M5 Pro (CPU). Per-call verdicts are in the dataset's results/ folder.
The file is named after the benchmark, so it doesn't touch any existing .eval_results file.
Updated to the v2 release.
Hi! This adds fastino/GLiNER2.5-Decide's results on the safeagents judge bench v2, a benchmark of real agent tool calls that safeagents' scanner flags as suspicious, each labelled block or allow and with a kind of misuse (reward hacking, harness introspection, credential misuse, ...).
On the 661 test calls: balanced accuracy 0.576, AUROC 0.517, false-block rate 0.0, category macro F1 0.355. Run zero-shot, one System One request per call, on Apple M5 Pro (CPU). Per-call verdicts are in the dataset's results/ folder.
The file is named after the benchmark, so it doesn't touch any existing .eval_results file. v2 keeps every earlier call and adds new ones (see the dataset card); these numbers replace the earlier ones in this file.