Downloads · 30 days
0
berturk-histr-lora-ner
cihanunlu/berturk-histr-lora-ner
berturk-histr-lora-ner is a token classification model from cihanunlu. Use it when you need labels on individual words, such as names. It is set up for transformers.
Attach it to the BerTurkOttomanFullDAPT checkpoint to obtain a lightweight NER model fine-tuned on the HiSTR corpus.
Access
Public
Updated Jun 10, 2025
Repo size
2.4 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.json3.2 MB · 48%
At a glance
- Task
- Token Classification
- Library
- transformers
- Access
- Public
- Created
- Jun 10, 2025
- Updated
- Jun 10, 2025
- SHA
- 166678fd
Base models
Datasets
Model card
From the Hugging Face model README
Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->Overview
| Base model | cihanunlu/BerTurk_Ottoman_Full_DAPT |
| Adapter type | LoRA (Low-Rank Adaptation) built with HF PEFT |
| Task | Named-Entity Recognition • BIO tags PER / LOC / O |
| Language | Ottoman / Late-Ottoman Turkish (Latin transliteration) |
| Repo contents | ≈ 2 MB LoRA weights (adapter_model.bin, adapter_config.json) + tokenizer files |
Attach it to the BerTurk_Ottoman_Full_DAPT checkpoint to obtain a lightweight NER model fine-tuned on the HiSTR corpus.
- • Suitable for historical/Ottoman Turkish NER focusing on PERSON and LOCATION.
- • Performance drops on modern Turkish or domain-specific jargon.
- • Adapter inherits ethical constraints and biases of the base BerTurk model.
3 Evaluation
-
Dev (HiSTR) — best checkpoint (epoch 4)
- Precision – 77.3 %
- Recall – 84.9 %
- F1 – 80.9 %
-
Test (Rûznâmçe)
- Precision – 54.4 %
- Recall – 52.8 %
- F1 – 53.6 %
4 Training hyper-parameters
- LoRA rank r: 16
- LoRA α: 16
- Dropout: 0.10
- Peak learning rate: 5 × 10⁻⁴
- Effective batch size: 16
- Epochs: 5
- Mixed precision: FP16
- Task
- Token Classification
- Library
- transformers
- Languages
- tr
- Created
- Jun 10, 2025
- Updated
- Jun 10, 2025