whr778/gliner2-base-v1-casie

gliner2-base-v1_casie

A GLiNER2 multi-task information-extraction model (entities, relations, events, and classification) fine-tuned from fastino/gliner2-base-v1.

⚠️ License at a glance

• Effective license: Unverified — review required
• Commercial use: Unverified
• All dataset licenses verified: No

See License for the full determination and per-dataset terms.

Model details

• Base model: fastino/gliner2-base-v1
• Library: gliner2
• Tasks: entity, relation, event, and classification extraction
• Experiment: gliner2-base-v1_casie

Training data

1 dataset used for this run. 798 training records (val: 95, test: 107).

Dataset	Task(s)	Train	Val	Test	Language	License	Source
CASIE	Event extraction (cybersecurity)	798	95	107	en	see source	link

Dataset notes

• CASIE — Cybersecurity event extraction co-trained with typed entity mentions; 5 event types, 26 argument roles.

Training procedure

Setting	Value
Trained on	2026-07-18
Duration	7m 47s
Throughput	21.3 samples/s
Epochs	15
Batch size	16 (× 2 grad-accum)
Encoder LR	1e-05
Task-head LR	0.0003
Weight decay	0.01
Scheduler	cosine_restarts (warmup 0.05)
Precision	bf16
Max grad norm	1.0
Best-checkpoint metric	eval_event_strict_micro_f1
Seed	42

Evaluation

Decision threshold: 0.5 (config default).

Blind test (held-out test splits)

Micro precision / recall / F1, strict → relaxed.

Category	Precision	Recall	F1	Support
entity	0.485 → 0.597	0.644 → 0.793	0.553 → 0.681	2136
event_type	1.000 → 1.000	0.865 → 0.865	0.928 → 0.928	185
event_trigger	0.656 → 0.779	0.301 → 0.357	0.413 → 0.490	856
event_argument	0.101 → 0.769	0.041 → 0.318	0.058 → 0.450	2413
event	0.338 → 0.797	0.150 → 0.360	0.207 → 0.496	3454

Best checkpoint (validation)

Micro precision / recall / F1, strict → relaxed.

Category	Precision	Recall	F1	Support
entity	0.553 → 0.668	0.628 → 0.759	0.588 → 0.711	2630
event_type	1.000 → 1.000	0.764 → 0.764	0.866 → 0.866	296
event_trigger	0.743 → 0.866	0.302 → 0.352	0.430 → 0.500	1006
event_argument	0.121 → 0.819	0.047 → 0.340	0.067 → 0.481	2706
event	0.391 → 0.855	0.164 → 0.376	0.231 → 0.523	4008

License

Effective license: Unverified — review required. This model is a derivative of its base model and every training dataset, so the most restrictive term across all of them governs the whole model.

• Commercial use: Unverified
• Share-alike obligation: No
• All licenses verified: No
• Base model: gliner2-base-v1 — see model card

Unverified — verify the upstream terms before redistribution

• CASIE (see source)
• gliner2-base-v1 (see model card)

License strings are copied verbatim from each dataset's card/source and from tools/train/dataset_registry.yaml. "see card"/"see source"/"other" mean the upstream declares no clear license — treat as unverified. This summary is informational, not legal advice; confirm terms before redistribution or commercial use.

Citation

If you use this model, please cite GLiNER2 and the underlying datasets (linked in Training data).

---

Model card generated automatically at the end of training (2026-07-18).