datasets: | |
- Kundyzka/informatics_kaz | |
language: | |
- kk | |
base_model: | |
- nur-dev/roberta-large-kazqad | |
pipeline_tag: question-answering | |
license: apache-2.0 | |
metrics: | |
- accuracy | |
- f1 | |
tags: | |
- informatics | |
library_name: transformers | |
# Model Card for roberta-large-kazqad-informatics_kaz | |
This model is a fine-tuned version of nur-dev/roberta-large-kazqad, adapted for question-answering tasks in the Kazakh language using the Kundyzka/informatics_kaz dataset. | |
## Model Details | |
### Model Description | |
This model has been optimized for question-answering in Kazakh within the domain of informatics. It leverages the RoBERTa architecture and has been trained to provide accurate responses to technical and academic questions in this field. | |
- **Developed by:** Tleubayeva Arailym, Saparbek Makhambet, Bassanova Nurgul, Shomanov Aday, [Sabitkhanov Askhat](https://huggingface.co/SayBitekhan) | |
- **Model type:** Transformer-based (RoBERTa) | |
- **Language(s) (NLP):** Kazakh (kk) | |
- **License:** apache-2.0 | |
## Evaluation | |
### Results | |
EM - 56,69(+316.2%) | |
F1 score- 69,70(+220.8%) | |
## Model Card Authors | |
Tleubayeva Arailym | |
Saparbek Makhambet | |
Bassanova Nurgul | |
[Sabitkhanov Askhat](https://huggingface.co/SayBitekhan) |