Downloads · 30 days
6
9% of all-time downloads
gliner2-large-v1-docee
whr778/gliner2-large-v1-docee
gliner2-large-v1-docee is a token classification model from whr778. Use it when you need labels on individual words, such as names. It is set up for gliner2. The card lists the license as other.
A GLiNER2 multi-task information-extraction model (entities, relations, events, and classification) fine-tuned from fastino/gliner2-large-v1.
All-time downloads
67
Public
Parameters
486M
1.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.9 GB · 100%
At a glance
- Task
- Token Classification
- Library
- gliner2
- License
- other
- Model type
- extractor
- Access
- Public
- Created
- Jul 20, 2026
- Updated
- Aug 6, 2026
- SHA
- aed9bbe9
Try a prompt
Base models
Model card
From the Hugging Face model README
gliner2-large-v1_docee
A 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 for the full determination and per-dataset terms.
Model details
- Base model:
fastino/gliner2-large-v1 - Library:
gliner2 - Tasks: entity, relation, event, and classification extraction
- Experiment:
gliner2-large-v1_docee
Training data
1 dataset used for this run. 21,966 training records (val: 2,748, test: 2,771).
| Dataset | Task(s) | Train | Val | Test | Language | License | Source |
|---|---|---|---|---|---|---|---|
| DocEE | Event extraction (doc-level) | 21,966 | 2,748 | 2,771 | en | see source | link |
Dataset notes
- DocEE — Document-level event extraction; one event per document mapped to role-typed entities and document classification.
Training procedure
| Setting | Value |
|---|---|
| Trained on | 2026-07-20 |
| Duration | 16h 30m |
| Throughput | 8.2 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_classification_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 | 0.296 → 0.467 | 0.460 → 0.727 | 0.360 → 0.569 | 19188 |
| classification | 0.994 → 0.997 | 0.994 → 0.997 | 0.994 → 0.997 | 2771 |
Best checkpoint (validation)
Micro precision / recall / F1, strict → relaxed.
| Category | Precision | Recall | F1 | Support |
|---|---|---|---|---|
| entity | 0.488 → 0.721 | 0.443 → 0.655 | 0.464 → 0.686 | 27078 |
| classification | 0.910 → 0.928 | 0.910 → 0.928 | 0.910 → 0.928 | 8093 |
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
- DocEE (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).
Model card generated automatically at the end of training (2026-07-20).
- Task
- Token Classification
- Library
- gliner2
- Type
- extractor
- License
- other
- Languages
- en
- Created
- Jul 20, 2026
- Updated
- Aug 6, 2026