-
jekunz/smollm-135m-cpt-fineweb-swedish-smol-smoltalk
Text Generation • 0.1B • Updated • 2 -
jekunz/smollm-135m-fineweb-swedish-from-scratch-smol-smoltalk
Text Generation • 0.1B • Updated • 3 -
jekunz/smollm-135m-cpt-fineweb-swedish
Text Generation • 0.1B • Updated • 12 -
jekunz/smollm-135m-fineweb-swedish-from-scratch
Text Generation • 0.1B • Updated • 7
Jenny Kunz
jekunz
AI & ML interests
Explainability and interpretability of NLP models, language adaptation, PEFT methods
Recent Activity
published
a dataset
4 days ago
liu-nlp/swedish-idioms
updated
a collection
4 days ago
Idiomatic Language Acquisition
updated
a collection
4 days ago
Idiomatic Language Acquisition
Organizations
SmolLM baselines trained from scratch
SmolLM CPT
Continued Pre-Training of SmolLM models on the Fineweb-2 portions of Scandinavian languages.
-
jekunz/smollm-135m-cpt-fineweb-faroese
Text Generation • 0.1B • Updated • 1 -
jekunz/smollm-135m-cpt-fineweb-icelandic
Text Generation • 0.1B • Updated • 2 -
jekunz/smollm-135m-cpt-fineweb-swedish
Text Generation • 0.1B • Updated • 12 -
jekunz/smollm-135m-cpt-fineweb-faroese-transfer-from-icelandic
Text Generation • 0.1B • Updated • 1
Idiomatic Language Acquisition
-
jekunz/smollm-135m-cpt-fineweb-swedish-smol-smoltalk
Text Generation • 0.1B • Updated • 2 -
jekunz/smollm-135m-fineweb-swedish-from-scratch-smol-smoltalk
Text Generation • 0.1B • Updated • 3 -
jekunz/smollm-135m-cpt-fineweb-swedish
Text Generation • 0.1B • Updated • 12 -
jekunz/smollm-135m-fineweb-swedish-from-scratch
Text Generation • 0.1B • Updated • 7
Adaptation of SmolLM to Faroese
All datasets and models created for the paper "Family Matters: Language Transfer and Merging for Adapting Small LLMs to Faroese".
SmolLM baselines trained from scratch
SmolLM CPT LoRA
SmolLM CPT
Continued Pre-Training of SmolLM models on the Fineweb-2 portions of Scandinavian languages.
-
jekunz/smollm-135m-cpt-fineweb-faroese
Text Generation • 0.1B • Updated • 1 -
jekunz/smollm-135m-cpt-fineweb-icelandic
Text Generation • 0.1B • Updated • 2 -
jekunz/smollm-135m-cpt-fineweb-swedish
Text Generation • 0.1B • Updated • 12 -
jekunz/smollm-135m-cpt-fineweb-faroese-transfer-from-icelandic
Text Generation • 0.1B • Updated • 1