---
library_name: gliner2
license: other
license_name: unverified-review-required
base_model: fastino/gliner2-base-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-base-v1_rams

A [GLiNER2](https://github.com/fastino-ai/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](#license) for the full determination and per-dataset terms.

## Model details

- **Base model:** [`fastino/gliner2-base-v1`](https://huggingface.co/fastino/gliner2-base-v1)
- **Library:** `gliner2`
- **Tasks:** entity, relation, event, and classification extraction
- **Experiment:** `gliner2-base-v1_rams`

## Training data

**1** dataset used for this run. 7,329 training records (val: 924, test: 871).

| Dataset | Task(s) | Train | Val | Test | Language | License | Source |
|---|---|--:|--:|--:|---|---|---|
| RAMS | Event extraction (trigger + args) | 7,329 | 924 | 871 | en | see source | [link](https://nlp.jhu.edu/rams/) |

**Dataset notes**

- **RAMS** — Multi-sentence event extraction with triggers and typed arguments; 139 event types, 65 argument roles.

## Training procedure

| Setting | Value |
|---|---|
| Trained on | 2026-07-19 |
| Duration | 28m 48s |
| Throughput | 63.6 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 |
|---|--:|--:|--:|--:|
| event_type | 1.000 → 1.000 | 0.986 → 0.986 | 0.993 → 0.993 | 848 |
| event_trigger | 0.927 → 0.929 | 0.943 → 0.946 | 0.935 → 0.937 | 848 |
| event_argument | 0.468 → 0.695 | 0.457 → 0.678 | 0.462 → 0.686 | 2016 |
| event | 0.697 → 0.819 | 0.689 → 0.810 | 0.693 → 0.814 | 3712 |

### Best checkpoint (validation)

Micro precision / recall / F1, strict → relaxed.

| Category | Precision | Recall | F1 | Support |
|---|--:|--:|--:|--:|
| event_type | 1.000 → 1.000 | 0.987 → 0.987 | 0.993 → 0.993 | 896 |
| event_trigger | 0.908 → 0.918 | 0.930 → 0.940 | 0.919 → 0.929 | 896 |
| event_argument | 0.422 → 0.677 | 0.396 → 0.634 | 0.408 → 0.655 | 2182 |
| event | 0.671 → 0.809 | 0.649 → 0.782 | 0.660 → 0.795 | 3974 |

## 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**
- RAMS (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](#training-data)).

---
_Model card generated automatically at the end of training (2026-07-19)._