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
-
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125
Text Generation • 8B • Updated • 135 • • 6 -
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825
Text Generation • 8B • Updated • 29 • 3 -
tartuNLP/Llama-3.1-EstLLM-8B-0525
Text Generation • 8B • Updated • 63 -
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
Paper • 2603.02041 • Published
Llama-2-based LLMs fine-tuned for grammatical error correction. This collection also includes AEG (Artificial Error Generation) models.
-
To Err Is Human, but Llamas Can Learn It Too
Paper • 2403.05493 • Published • 6 -
tartuNLP/Llamma-2-7b-ukr-p1-llama-errors-p2-GEC
Text Generation • 7B • Updated • 25 • 2 -
tartuNLP/Llammas-base-p1-llama-errors-p2-GEC
Text Generation • 7B • Updated • 29 • 3 -
tartuNLP/leo-hessianai-7b-p1-llama-errors-p2-GEC
Text Generation • 7B • Updated • 11
-
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125
Text Generation • 8B • Updated • 135 • • 6 -
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825
Text Generation • 8B • Updated • 29 • 3 -
tartuNLP/Llama-3.1-EstLLM-8B-0525
Text Generation • 8B • Updated • 63 -
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
Paper • 2603.02041 • Published
A collection of resources for evaluation of LLM capabilities in the Estonian language.
Llama-2-based LLMs fine-tuned for grammatical error correction. This collection also includes AEG (Artificial Error Generation) models.
-
To Err Is Human, but Llamas Can Learn It Too
Paper • 2403.05493 • Published • 6 -
tartuNLP/Llamma-2-7b-ukr-p1-llama-errors-p2-GEC
Text Generation • 7B • Updated • 25 • 2 -
tartuNLP/Llammas-base-p1-llama-errors-p2-GEC
Text Generation • 7B • Updated • 29 • 3 -
tartuNLP/leo-hessianai-7b-p1-llama-errors-p2-GEC
Text Generation • 7B • Updated • 11