AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
Teaching Old Tokenizers New Words: Efficient Tokenizer Adaptation for Pre-trained Models
Organization Card
We are the research group of natural language processing at the Institute of Computer Science, University of Tartu. Our areas of focus include machine translation, speech synthesis, NLP for Estonian and others.
-
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125
Text Generation • 8B • Updated • 625 • • 6 -
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825
Text Generation • 8B • Updated • 328 • 3 -
tartuNLP/Llama-3.1-EstLLM-8B-0525
Text Generation • 8B • Updated • 285 • -
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
Paper • 2603.02041 • Published
-
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125
Text Generation • 8B • Updated • 625 • • 6 -
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825
Text Generation • 8B • Updated • 328 • 3 -
tartuNLP/Llama-3.1-EstLLM-8B-0525
Text Generation • 8B • Updated • 285 • -
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
Paper • 2603.02041 • Published
models 78
tartuNLP/Llama-3.1-EstLLM-70B-0826
Text Generation • 71B • Updated • 1.4k
tartuNLP/est-roberta-hist-ner
Token Classification • 0.1B • Updated • 57
tartuNLP/est-roberta-hist-ner-for-tccp
Token Classification • 0.1B • Updated • 50
tartuNLP/est-roberta-vm-morph-tagging
Token Classification • 0.1B • Updated • 24
tartuNLP/est-roberta-vm-morph-homonym-tagging
Token Classification • 0.1B • Updated • 12
tartuNLP/Llama-3.1-EstLLM-70B-Instruct-0826
Text Generation • 71B • Updated • 1.46k
tartuNLP/Llama-3.1-EstLLM-8B-0525
Text Generation • 8B • Updated • 285 •
tartuNLP/EstBERT_NER_v2
Token Classification • 0.1B • Updated • 634 • 1
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125
Text Generation • 8B • Updated • 625 • • 6
tartuNLP/Apertus-EstLLM-8B-Instruct-1125
Text Generation • 8B • Updated • 217 • 1
datasets 37
tartuNLP/Estonian_Subjectivity
Viewer • Updated • 1k • 435
tartuNLP/winogrande_et
Viewer • Updated • 8.36k • 113 • 1
tartuNLP/SynEstParallel
Viewer • Updated • 1.61B • 297
tartuNLP/sib-smugri
Viewer • Updated • 3.1k • 134
tartuNLP/belebele-smugri
Viewer • Updated • 381 • 50
tartuNLP/wikipedia-smugri-20251201
Viewer • Updated • 1.47M • 93
tartuNLP/smugri4-data
Updated • 58 • 1
tartuNLP/EstSpeechMT
Updated • 14
tartuNLP/finepdfs-et
Viewer • Updated • 554k • 35
tartuNLP/finetranslations-et
Viewer • Updated • 10M • 138