Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- tr
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card: Turkish Scientific RoBERTa ONNX
|
| 7 |
+
|
| 8 |
+
## Model Description
|
| 9 |
+
ONNX version of roberta-base-turkish-scientific-cased, specialized for Turkish scientific text analysis.
|
| 10 |
+
|
| 11 |
+
## Intended Use
|
| 12 |
+
- Scientific text analysis in Turkish
|
| 13 |
+
- Text comprehension
|
| 14 |
+
- Fill-mask predictions
|
| 15 |
+
- Scientific text summarization
|
| 16 |
+
|
| 17 |
+
## Training Data
|
| 18 |
+
- Source: Turkish scientific article abstracts from trdizin, yöktez, and t.k.
|
| 19 |
+
- Training Duration: 3+ days
|
| 20 |
+
- Steps: 2M
|
| 21 |
+
- Built from scratch, no fine-tuning
|
| 22 |
+
|
| 23 |
+
## Technical Specifications
|
| 24 |
+
- Base Architecture: RoBERTa
|
| 25 |
+
- Tokenizer: BPE (Byte Pair Encoding)
|
| 26 |
+
- Format: ONNX
|
| 27 |
+
- Original Model: serdarcaglar/roberta-base-turkish-scientific-cased
|
| 28 |
+
|
| 29 |
+
## Performance and Limitations
|
| 30 |
+
- Optimized for scientific domain in Turkish
|
| 31 |
+
- Not tested for general domain text
|
| 32 |
+
- ONNX format optimized for inference
|
| 33 |
+
|
| 34 |
+
## Requirements
|
| 35 |
+
- onnxruntime
|
| 36 |
+
- transformers
|
| 37 |
+
- torch
|
| 38 |
+
|
| 39 |
+
## License and Usage
|
| 40 |
+
- Follow original model license
|
| 41 |
+
- Users responsible for compliance
|
| 42 |
+
|
| 43 |
+
## Citation
|
| 44 |
+
```bibtex
|
| 45 |
+
@misc{caglar2024roberta,
|
| 46 |
+
author = {Çağlar, Serdar},
|
| 47 |
+
title = {Roberta-base-turkish-scientific-cased},
|
| 48 |
+
year = {2024},
|
| 49 |
+
publisher = {HuggingFace},
|
| 50 |
+
url = {https://huggingface.co/serdarcaglar/roberta-base-turkish-scientific-cased}
|
| 51 |
+
}
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
## Contact
|
| 55 |
+
Serdar ÇAĞLAR ([email protected])
|