COPATeam/armenian_llm_ecosystem
This repository contains the complete reproduction code for the research paper "From Zero to Hero: An Open LLM Ecosystem for Armenian". It provides pipelines for building the ArmWeb corpus (4.37M Armenian news documents) and the ArmSTEM dataset (373K verified parallel STEM problems), along with training recipes for continued pretraining of LLMs (like Gemma) on Armenian data and evaluation harnesses.
A project to build a Large Language Model (LLM) specifically for the Armenian language from scratch using PyTorch and...
A training repository for a workshop on lightweight NLP models for under-resourced languages, specifically Armenian. ...
A curated list of Armenian language datasets, corpora, models, and digital resources for NLP and computational lingui...
ArmGPT is a student-friendly implementation of a GPT language model specifically trained on Armenian text. It's built...
A project exploring Armenian language autocomplete using multiple NLP approaches including Word2Vec, LSTM, BERT trans...
ArmBench-LLM is a specialized evaluation framework for benchmarking large language models on Armenian language tasks....