Dan Saattrup Smart

### Model ID Finnish-NLP/Ahma-7B ### Evaluation languages - [ ] Romance languages (French, Italian, Portuguese, Spanish) - [ ] Scandinavian languages (Danish, Faroese, Icelandic, Norwegian, Swedish) - [ ] West...

### Model ID Finnish-NLP/Ahma-3B ### Evaluation languages - [ ] Romance languages (French, Italian, Portuguese, Spanish) - [ ] Scandinavian languages (Danish, Faroese, Icelandic, Norwegian, Swedish) - [ ] West...

### Model ID Finnish-NLP/Ahma-3B-Instruct ### Evaluation languages - [ ] Romance languages (French, Italian, Portuguese, Spanish) - [ ] Scandinavian languages (Danish, Faroese, Icelandic, Norwegian, Swedish) - [ ] West...

### Language name and code West Frisian (fy) ### Sentiment classification dataset _No response_ ### Linguistic acceptability dataset ScaLA algorithm with Frisian Universal Dependencies (either [this one](https://github.com/UniversalDependencies/UD_Frisian-Frysk/tree/dev) or [this one](https://github.com/UniversalDependencies/UD_Frisian_Dutch-Fame))...

### Language name and code Basque (eu) ### Sentiment classification dataset - [Multibooked](https://github.com/jerbarnes/multibooked) - [BEC2016eu](https://huggingface.co/datasets/orai-nlp/basqueGLUE) ### Linguistic acceptability dataset - [BL2MP](https://huggingface.co/datasets/orai-nlp/bl2mp) - ScaLA algorithm with [Basque Universal Dependencies](https://github.com/UniversalDependencies/UD_Basque-BDT) ### Named...

### Language name and code Scots (sco) ### Sentiment classification dataset _No response_ ### Linguistic acceptability dataset _No response_ ### Named entity recognition dataset [WikiANN-sco](https://huggingface.co/datasets/unimelb-nlp/wikiann/viewer/sco) ### Reading comprehension dataset [MultiWikiQA-sco](https://huggingface.co/datasets/alexandrainst/multi-wiki-qa/viewer/sco)...

### Language name and code Belarusian (be) ### Sentiment classification dataset [BeSLS](https://huggingface.co/datasets/maaxap/BelarusianGLUE/viewer/besls) ### Linguistic acceptability dataset - ScaLA algorithm with the [Belarusian Universal Dependencies](https://github.com/UniversalDependencies/UD_Belarusian-HSE) - [BelaCoLA](https://huggingface.co/datasets/maaxap/BelarusianGLUE/viewer/belacola_out_of_domain?views%5B%5D=belacola_out_of_domain_validation) (both in-domain and out-of-domain)...

### Language name and code Albanian (sq) ### Sentiment classification dataset [MMS-sq](https://huggingface.co/datasets/Brand24/mms) ### Linguistic acceptability dataset ScaLA algorithm with the [Albanian Universal Dependencies](https://github.com/UniversalDependencies/UD_Albanian-STAF) ### Named entity recognition dataset [WikiANN-sq](https://huggingface.co/datasets/unimelb-nlp/wikiann/viewer/sq) ###...

### Language name and code Irish (ga) ### Sentiment classification dataset _No response_ ### Linguistic acceptability dataset ScaLA algorithm with the [Irish Universal Dependencies](https://github.com/UniversalDependencies/UD_Irish-IDT) ### Named entity recognition dataset [WikiANN-ga](https://huggingface.co/datasets/unimelb-nlp/wikiann/viewer/ga)...

### Language name and code Macedonian (mk) ### Sentiment classification dataset _No response_ ### Linguistic acceptability dataset ScaLA algorithm with the [Macedonian Universal Dependencies](https://github.com/UniversalDependencies/UD_Macedonian-MTB) ### Named entity recognition dataset [WikiANN-mk](https://huggingface.co/datasets/unimelb-nlp/wikiann/viewer/mk)...