---
tags:
  - gliner2
  - ner
  - data-mention-extraction
  - lora
base_model: fastino/gliner2-large-v1
library_name: gliner2
---

# GLiNER2 Data Mention Extractor (v15-transformed)

Fine-tuned GLiNER2 LoRA adapter for extracting structured data mentions from
development economics and humanitarian research documents.

**v4 key change:** Trained with a patched GLiNER2 library
(`rafmacalaba/GLiNER2@feat/main-fixes-clw`) that feeds mean-pooled passage token embeddings
into `count_pred` instead of the schema `[P]` token. This is the first adapter
version where multi-mention recall is trained via a meaningful gradient.

## Task

Given a document passage, extracts structured information about each dataset mentioned:

- **Extractive field**: `mention_name` (verbatim from text)
- **Classification fields** (fixed choices):
  - `specificity_tag`: named / descriptive / vague
  - `typology_tag`: survey / census / database / administrative / indicator / geospatial / microdata / report / other
  - `is_used`: True / False
  - `usage_context`: primary / supporting / background

## Training

- **Base model**: `fastino/gliner2-large-v1`
- **Method**: LoRA (r=16, alpha=32.0)
- **Target modules**: ['encoder', 'span_rep', 'classifier', 'count_embed', 'count_pred']
- **Training examples**: 1430
- **Val examples**: 136
- **Best val loss**: 379.9630
- **GLiNER2 branch**: `rafmacalaba/GLiNER2@feat/main-fixes-clw`

## Usage

```python
from gliner2 import GLiNER2

# Install the patched library first
# pip install git+https://github.com/rafmacalaba/GLiNER2.git@feat/main-fixes-clw

extractor = GLiNER2.from_pretrained("fastino/gliner2-large-v1")
extractor.load_adapter("rafmacalaba/gliner2-datause-large-v15-transformed")

schema = (
    extractor.create_schema()
    .structure("data_mention")
        .field("mention_name",    dtype="str")
        .field("specificity_tag", dtype="str", choices=["named", "descriptive", "vague", "na"])
        .field("typology_tag",    dtype="str", choices=["survey", "census", "administrative",
                                                         "database", "indicator", "geospatial",
                                                         "microdata", "report", "other", "na"])
        .field("is_used",         dtype="str", choices=["True", "False", "na"])
        .field("usage_context",   dtype="str", choices=["primary", "supporting", "background", "na"])
)

result = extractor.extract(text, schema)
```