Nasjonalbiblioteket AI Lab

Team

non-profit

Verified

https://ai.nb.no/

NbAiLab

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

versae updated a dataset 10 days ago

NbAiLab/nb-fineweb2-edu-bokmaal

versae updated a dataset 10 days ago

NbAiLab/nb-fineweb2-edu-bokmaal

titae authored a paper 3 months ago

NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark

View all activity

NbAiLab 's collections 10

NB-Whisper

Models based on Whisper from OpenAI, and trained on data from Språkbanken and the digital collection at the National Library of Norway.

NbAiLab/nb-whisper-large-distil-turbo-beta

Automatic Speech Recognition • 0.8B • Updated Nov 30, 2024 • 3.15k • 2
NbAiLab/nb-whisper-large

Automatic Speech Recognition • 2B • Updated Jul 13, 2024 • 2.16k • 26
NbAiLab/nb-whisper-medium

Automatic Speech Recognition • 0.8B • Updated Feb 13, 2024 • 1.29k • 4
NbAiLab/nb-whisper-small

Automatic Speech Recognition • 0.2B • Updated Feb 13, 2024 • 1.34k • 1

NB-Llama 3.x Quant

Quantized version of the NB-Llama 3.x models. Due to hardware issues, we have still not been able to make quantized version of the 70B models.

NbAiLab/nb-llama-3.2-1B-Q4_K_M-GGUF

Text Generation • 1B • Updated Dec 11, 2024 • 9
NbAiLab/nb-llama-3.2-3B-Q4_K_M-GGUF

Text Generation • 3B • Updated Dec 11, 2024 • 6
NbAiLab/nb-llama-3.1-8B-Q4_K_M-GGUF

Text Generation • 8B • Updated Dec 11, 2024 • 25
NbAiLab/nb-llama-3.2-1B-Instruct-Q4_K_M-GGUF

Text Generation • 1B • Updated Dec 11, 2024 • 11

NB-Wav2Vec

Models based on Wav2Vec from Meta, and trained on data from Språkbanken and the digital collection at the National Library of Norway.

Boosting Norwegian Automatic Speech Recognition

Paper • 2307.01672 • Published Jul 4, 2023 • 1
NbAiLab/nb-wav2vec2-300m-bokmaal-v2

Automatic Speech Recognition • 0.3B • Updated Oct 14, 2024 • 8.63k
NbAiLab/nb-wav2vec2-300m-bokmaal

Automatic Speech Recognition • 0.3B • Updated Dec 9, 2024 • 107
NbAiLab/nb-wav2vec2-1b-bokmaal-v2

Automatic Speech Recognition • 1.0B • Updated Dec 27, 2024 • 78.4k

NB-BERT

Models based on BERT from Google, and trained on data from various sources, including the digital collection at the National Library of Norway.

Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model

Paper • 2104.09617 • Published Apr 19, 2021
NbAiLab/nb-bert-base

Fill-Mask • 0.2B • Updated Sep 7, 2023 • 1.64k • • 30
NbAiLab/nb-bert-large

Fill-Mask • 0.4B • Updated Sep 11, 2023 • 290 • 13

Newspaper Processing

Tools for processing of newspapers: cropping (TBD) and front page detection.

NbAiLab/vit-front-page-384-complete-v2

Image Classification • 0.1B • Updated Feb 4 • 13
NbAiLab/vit-front-page-384-top-v2

Image Classification • 0.1B • Updated Feb 4 • 9

NB-Llama 3.x

NOTE: CURRENTLY THERE ARE CONVERTION-ERRORS IN THIS MODELS. TEMPORARY PUT OFFLINE. LLama 3.x models in various sizes.

NbAiLab/nb-llama-3.2-1B

Text Generation • 1B • Updated Dec 11, 2024 • 30 • • 2

NB-Whisper-verbatim

NB-Whisper models that are mostly suited for linguists and researchers. The output is lowercase and without punctation.

NbAiLab/nb-whisper-large-verbatim

Automatic Speech Recognition • 2B • Updated Feb 13, 2024 • 1.39k • 2
NbAiLab/nb-whisper-medium-verbatim

Automatic Speech Recognition • 0.8B • Updated Feb 13, 2024 • 6
NbAiLab/nb-whisper-small-verbatim

Automatic Speech Recognition • 0.2B • Updated Feb 13, 2024 • 9
NbAiLab/nb-whisper-base-verbatim

Automatic Speech Recognition • 0.1B • Updated Feb 13, 2024 • 3

NB-GPT-J

Models based on GPT-J from EleutherAI, and trained on data from various sources, including the digital collection at the National Library of Norway.

NbAiLab/nb-gpt-j-6B

Text Generation • 6B • Updated Sep 20, 2023 • 16 • 20
NbAiLab/nb-gpt-j-6B-v2

Text Generation • 6B • Updated Nov 21, 2023 • 222 • 3
NbAiLab/nb-gpt-j-6B-alpaca

Text Generation • 6B • Updated Sep 20, 2023 • 227 • 2
NbAiLab/nb-gpt-j-6B-norpaca

Text Generation • Updated Sep 20, 2023 • 6

Speech datasets

Speech data for our speech to text models

NbAiLab/NST

Updated May 20 • 272 • 3
NbAiLab/NPSC

Updated Aug 14, 2024 • 620 • 8
NbAiLab/NST_hesitate

Updated Sep 10, 2024 • 28

NB-Whisper Beta

Models based on Whisper from OpenAI, and trained on data from Språkbanken and the digital collection at the National Library of Norway.

NbAiLab/nb-whisper-tiny-beta

Automatic Speech Recognition • 0.0B • Updated Jul 24, 2023 • 5 • 1
NbAiLab/nb-whisper-base-beta

Automatic Speech Recognition • 0.1B • Updated Jul 24, 2023 • 6 • 1
NbAiLab/nb-whisper-small-beta

Automatic Speech Recognition • 0.2B • Updated Jul 23, 2023 • 28 • 15
NbAiLab/nb-whisper-medium-beta

Automatic Speech Recognition • 0.8B • Updated Jul 24, 2023 • 5 • 2

NB-Whisper

Models based on Whisper from OpenAI, and trained on data from Språkbanken and the digital collection at the National Library of Norway.

NbAiLab/nb-whisper-large-distil-turbo-beta

Automatic Speech Recognition • 0.8B • Updated Nov 30, 2024 • 3.15k • 2
NbAiLab/nb-whisper-large

Automatic Speech Recognition • 2B • Updated Jul 13, 2024 • 2.16k • 26
NbAiLab/nb-whisper-medium

Automatic Speech Recognition • 0.8B • Updated Feb 13, 2024 • 1.29k • 4
NbAiLab/nb-whisper-small

Automatic Speech Recognition • 0.2B • Updated Feb 13, 2024 • 1.34k • 1

NB-Llama 3.x

NOTE: CURRENTLY THERE ARE CONVERTION-ERRORS IN THIS MODELS. TEMPORARY PUT OFFLINE. LLama 3.x models in various sizes.

NbAiLab/nb-llama-3.2-1B

Text Generation • 1B • Updated Dec 11, 2024 • 30 • • 2

NB-Llama 3.x Quant

Quantized version of the NB-Llama 3.x models. Due to hardware issues, we have still not been able to make quantized version of the 70B models.

NbAiLab/nb-llama-3.2-1B-Q4_K_M-GGUF

Text Generation • 1B • Updated Dec 11, 2024 • 9
NbAiLab/nb-llama-3.2-3B-Q4_K_M-GGUF

Text Generation • 3B • Updated Dec 11, 2024 • 6
NbAiLab/nb-llama-3.1-8B-Q4_K_M-GGUF

Text Generation • 8B • Updated Dec 11, 2024 • 25
NbAiLab/nb-llama-3.2-1B-Instruct-Q4_K_M-GGUF

Text Generation • 1B • Updated Dec 11, 2024 • 11

NB-Whisper-verbatim

NB-Whisper models that are mostly suited for linguists and researchers. The output is lowercase and without punctation.

NbAiLab/nb-whisper-large-verbatim

Automatic Speech Recognition • 2B • Updated Feb 13, 2024 • 1.39k • 2
NbAiLab/nb-whisper-medium-verbatim

Automatic Speech Recognition • 0.8B • Updated Feb 13, 2024 • 6
NbAiLab/nb-whisper-small-verbatim

Automatic Speech Recognition • 0.2B • Updated Feb 13, 2024 • 9
NbAiLab/nb-whisper-base-verbatim

Automatic Speech Recognition • 0.1B • Updated Feb 13, 2024 • 3

NB-Wav2Vec

Models based on Wav2Vec from Meta, and trained on data from Språkbanken and the digital collection at the National Library of Norway.

Boosting Norwegian Automatic Speech Recognition

Paper • 2307.01672 • Published Jul 4, 2023 • 1
NbAiLab/nb-wav2vec2-300m-bokmaal-v2

Automatic Speech Recognition • 0.3B • Updated Oct 14, 2024 • 8.63k
NbAiLab/nb-wav2vec2-300m-bokmaal

Automatic Speech Recognition • 0.3B • Updated Dec 9, 2024 • 107
NbAiLab/nb-wav2vec2-1b-bokmaal-v2

Automatic Speech Recognition • 1.0B • Updated Dec 27, 2024 • 78.4k

NB-GPT-J

Models based on GPT-J from EleutherAI, and trained on data from various sources, including the digital collection at the National Library of Norway.

NbAiLab/nb-gpt-j-6B

Text Generation • 6B • Updated Sep 20, 2023 • 16 • 20
NbAiLab/nb-gpt-j-6B-v2

Text Generation • 6B • Updated Nov 21, 2023 • 222 • 3
NbAiLab/nb-gpt-j-6B-alpaca

Text Generation • 6B • Updated Sep 20, 2023 • 227 • 2
NbAiLab/nb-gpt-j-6B-norpaca

Text Generation • Updated Sep 20, 2023 • 6

NB-BERT

Models based on BERT from Google, and trained on data from various sources, including the digital collection at the National Library of Norway.

Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model

Paper • 2104.09617 • Published Apr 19, 2021
NbAiLab/nb-bert-base

Fill-Mask • 0.2B • Updated Sep 7, 2023 • 1.64k • • 30
NbAiLab/nb-bert-large

Fill-Mask • 0.4B • Updated Sep 11, 2023 • 290 • 13

Speech datasets

Speech data for our speech to text models

NbAiLab/NST

Updated May 20 • 272 • 3
NbAiLab/NPSC

Updated Aug 14, 2024 • 620 • 8
NbAiLab/NST_hesitate

Updated Sep 10, 2024 • 28

Newspaper Processing

Tools for processing of newspapers: cropping (TBD) and front page detection.

NbAiLab/vit-front-page-384-complete-v2

Image Classification • 0.1B • Updated Feb 4 • 13
NbAiLab/vit-front-page-384-top-v2

Image Classification • 0.1B • Updated Feb 4 • 9

NB-Whisper Beta

Models based on Whisper from OpenAI, and trained on data from Språkbanken and the digital collection at the National Library of Norway.

NbAiLab/nb-whisper-tiny-beta

Automatic Speech Recognition • 0.0B • Updated Jul 24, 2023 • 5 • 1
NbAiLab/nb-whisper-base-beta

Automatic Speech Recognition • 0.1B • Updated Jul 24, 2023 • 6 • 1
NbAiLab/nb-whisper-small-beta

Automatic Speech Recognition • 0.2B • Updated Jul 23, 2023 • 28 • 15
NbAiLab/nb-whisper-medium-beta

Automatic Speech Recognition • 0.8B • Updated Jul 24, 2023 • 5 • 2

AI & ML interests

Recent Activity

Team members 16

NbAiLab 's collections 10