khachaturnalbandyan/tiny-gpt-armenian
A 10.8M-parameter GPT written from scratch in PyTorch and trained on Armenian Wikipedia in 8 minutes on a laptop GPU.
A small character-level GPT trained on Armenian Wikipedia, implemented in PyTorch with data preparation, training, sample outputs, and attention results. It is primarily an educational/demo project for Armenian language modeling.
ArmGPT is a student-friendly implementation of a GPT language model specifically trained on Armenian text. It's built...
Decoder-only Armenian GPT trained from scratch on ArmWeb and Wikipedia corpora, with BPE tokenization, notebooks for ...
A Western Armenian language model project using transformer architecture, implemented in Jupyter notebooks. Includes ...
A project to create a bilingual Western Armenian-English large language model using QLoRA fine-tuning on Qwen 2.5 1.5...
A project exploring Armenian language autocomplete using multiple NLP approaches including Word2Vec, LSTM, BERT trans...
A Western Armenian language assistant designed for WordPress integration. It's a full-stack application using Supabas...