README.md

---
library_name: gliner2
license: other
license_name: unverified-review-required
base_model: fastino/gliner2-large-v1
language:
  - en
tags:
  - gliner2
  - information-extraction
  - named-entity-recognition
  - relation-extraction
  - event-extraction
  - text-classification
metrics:
  - f1
  - precision
  - recall
pipeline_tag: token-classification
---

# gliner2-large-v1_wikievents

A [GLiNER2](https://github.com/fastino-ai/GLiNER2) multi-task information-extraction model (entities, relations, events, and classification) fine-tuned from `fastino/gliner2-large-v1`.

## ⚠️ License at a glance

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

See [License](#license) for the full determination and per-dataset terms.

## Model details

- **Base model:** [`fastino/gliner2-large-v1`](https://huggingface.co/fastino/gliner2-large-v1)
- **Library:** `gliner2`
- **Tasks:** entity, relation, event, and classification extraction
- **Experiment:** `gliner2-large-v1_wikievents`

## Training data

**1** dataset used for this run. 206 training records (val: 20, test: 20).

| Dataset | Task(s) | Train | Val | Test | Language | License | Source |
|---|---|--:|--:|--:|---|---|---|
| WikiEvents | NER + event extraction | 206 | 20 | 20 | en | see source | [link](https://github.com/raspberryice/gen-arg) |

**Dataset notes**

- **WikiEvents** — KAIROS-ontology event extraction co-trained with typed entity mentions; 49 event types, 57 argument roles.

## Training procedure

| Setting | Value |
|---|---|
| Trained on | 2026-07-20 |
| Duration | 12m 8s |
| Throughput | 10.3 samples/s |
| Epochs | 15 |
| Batch size | 4 (× 8 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 | 0.767 → 0.803 | 0.818 → 0.857 | 0.792 → 0.829 | 1602 |
| event_type | 1.000 → 1.000 | 0.926 → 0.926 | 0.962 → 0.962 | 122 |
| event_trigger | 0.499 → 0.510 | 0.703 → 0.720 | 0.583 → 0.597 | 239 |
| event_argument | 0.114 → 0.455 | 0.124 → 0.479 | 0.119 → 0.467 | 515 |
| event | 0.342 → 0.539 | 0.394 → 0.613 | 0.366 → 0.574 | 876 |

### Best checkpoint (validation)

Micro precision / recall / F1, strict → relaxed.

| Category | Precision | Recall | F1 | Support |
|---|--:|--:|--:|--:|
| entity | 0.736 → 0.789 | 0.738 → 0.792 | 0.737 → 0.790 | 2519 |
| event_type | 1.000 → 1.000 | 0.717 → 0.717 | 0.835 → 0.835 | 276 |
| event_trigger | 0.777 → 0.801 | 0.487 → 0.502 | 0.599 → 0.617 | 464 |
| event_argument | 0.270 → 0.644 | 0.156 → 0.393 | 0.198 → 0.488 | 621 |
| event | 0.614 → 0.782 | 0.383 → 0.500 | 0.472 → 0.610 | 1361 |

## 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-large-v1 — see model card

**Unverified — verify the upstream terms before redistribution**
- WikiEvents (see source)
- gliner2-large-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](#training-data)).

---
_Model card generated automatically at the end of training (2026-07-20)._