NorBERT-3
Browse files
README.md
CHANGED
|
@@ -30,4 +30,15 @@ _Andrey Kutuzov, Jeremy Barnes, Erik Velldal, Lilja Øvrelid, Stephan Oepen. [La
|
|
| 30 |
NorBERT was trained as a part of NorLM, a joint initiative of the projects [EOSC-Nordic](https://www.eosc-nordic.eu/) (European Open Science Cloud),
|
| 31 |
coordinated by the [Language Technology Group](https://www.mn.uio.no/ifi/english/research/groups/ltg/) (LTG) at the University of Oslo.
|
| 32 |
|
| 33 |
-
The computations were performed on resources provided by UNINETT Sigma2 - the National Infrastructure for High Performance Computing and Data Storage in Norway.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
NorBERT was trained as a part of NorLM, a joint initiative of the projects [EOSC-Nordic](https://www.eosc-nordic.eu/) (European Open Science Cloud),
|
| 31 |
coordinated by the [Language Technology Group](https://www.mn.uio.no/ifi/english/research/groups/ltg/) (LTG) at the University of Oslo.
|
| 32 |
|
| 33 |
+
The computations were performed on resources provided by UNINETT Sigma2 - the National Infrastructure for High Performance Computing and Data Storage in Norway.
|
| 34 |
+
|
| 35 |
+
## NorBERT-3
|
| 36 |
+
In 2023, we released a new family of *NorBERT-3* language models for Norwegian. In general, we now recommend using these models:
|
| 37 |
+
|
| 38 |
+
- [NorBERT 3 xs](https://huggingface.co/ltg/norbert3-xs) (15M parameters)
|
| 39 |
+
- [NorBERT 3 small](https://huggingface.co/ltg/norbert3-small) (40M parameters)
|
| 40 |
+
- [NorBERT 3 base](https://huggingface.co/ltg/norbert3-base) (123M parameters)
|
| 41 |
+
- [NorBERT 3 large](https://huggingface.co/ltg/norbert3-large) (323M parameters)
|
| 42 |
+
|
| 43 |
+
NorBERT-3 is described in detail in this paper:
|
| 44 |
+
[NorBench – A Benchmark for Norwegian Language Models](https://aclanthology.org/2023.nodalida-1.61/) (Samuel et al., NoDaLiDa 2023)
|