Edit model card

Model is developed in support of the University of Belgrade doctoral dissertation "Composite pseudogrammars based on parallel language models of Serbian" by Mihailo Škorić.

It generates syntactly masked sentences for Serbian.

This small gpt-2 model was fine-tuned on several corpora for Serbian, augmented using Serbian Morphological Dictionaries).

The corpora include "The corpus of Contemporary Serbian", SrpELTeC and WikiKorpus by JeRTeh – Society for Language Resources and Technologies.

This model is purely experimental! For actual models for Serbian see GPT2-ORAO and GPT2-VRABAC
If you use this model for your reseach please cite: https://doi.org/10.3390/math11224660

Downloads last month
5
Safetensors
Model size
138M params
Tensor type
F32
·
U8
·