The first release of the Munin models by the Danish Foundation Models project, being existing base models post-trained for Danish and English.
AI & ML interests
None defined yet.
Recent Activity
View all activity
A collection of EuroEval compatible datasets which can be run using: `euroeval --dataset {dataset name} --model {model name}`
This is a collection of artifact released as a part of the paper: "Dynaword: From One-shot to Continuously Developed Datasets".
-
Dynaword: From One-shot to Continuously Developed Datasets
Paper • 2508.02271 • Published • 15 -
danish-foundation-models/danish-dynaword
Viewer • Updated • 22.2M • 5.8k • 22 -
danish-foundation-models/gemma-3-1b-cpt-dynaword-matched-v1
Text Generation • 1.0B • Updated • 6 -
danish-foundation-models/gemma-3-1b-scratch-dynaword-full-v1
Text Generation • 1.0B • Updated • 12
These include high-quality Danish text datasets for pre-training, fine-tuning, etc.
These models constitute state-of-the-art models for Danish within their respective domain (highlighted below the model).
-
mistralai/Mistral-Small-3.1-24B-Instruct-2503
24B • Updated • 146k • 1.38k -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 451k • • 2.02k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 25.1k • • 920 -
google/gemma-2-9b-it
Text Generation • 9B • Updated • 674k • • 915
A collection of dynawords, target various languages
Datasets related to AI-Arenaen
-
danish-foundation-models/ai-arenaen-conversations
Viewer • Updated • 3.09k • 11 • 1 -
danish-foundation-models/ai-arenaen-reactions
Preview • Updated • 3 • 1 -
danish-foundation-models/ai-arenaen-votes
Viewer • Updated • 1.77k • 3 • 1 -
ministere-culture/comparia-conversations
Viewer • Updated • 410k • 70 • 72
Papers related to Danish Foundation Models
Benchmarks for evaluating Danish Models.
-
EuroEval Leaderboard
📊8The robust European language model benchmark.
-
ScandEval: A Benchmark for Scandinavian Natural Language Processing
Paper • 2304.00906 • Published • 4 -
MTEB Leaderboard
📊7.64kEmbedding Leaderboard
-
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
Paper • 2406.02396 • Published • 1
The first release of the Munin models by the Danish Foundation Models project, being existing base models post-trained for Danish and English.
A collection of dynawords, target various languages
A collection of EuroEval compatible datasets which can be run using: `euroeval --dataset {dataset name} --model {model name}`
Datasets related to AI-Arenaen
-
danish-foundation-models/ai-arenaen-conversations
Viewer • Updated • 3.09k • 11 • 1 -
danish-foundation-models/ai-arenaen-reactions
Preview • Updated • 3 • 1 -
danish-foundation-models/ai-arenaen-votes
Viewer • Updated • 1.77k • 3 • 1 -
ministere-culture/comparia-conversations
Viewer • Updated • 410k • 70 • 72
This is a collection of artifact released as a part of the paper: "Dynaword: From One-shot to Continuously Developed Datasets".
-
Dynaword: From One-shot to Continuously Developed Datasets
Paper • 2508.02271 • Published • 15 -
danish-foundation-models/danish-dynaword
Viewer • Updated • 22.2M • 5.8k • 22 -
danish-foundation-models/gemma-3-1b-cpt-dynaword-matched-v1
Text Generation • 1.0B • Updated • 6 -
danish-foundation-models/gemma-3-1b-scratch-dynaword-full-v1
Text Generation • 1.0B • Updated • 12
Papers related to Danish Foundation Models
These include high-quality Danish text datasets for pre-training, fine-tuning, etc.
Benchmarks for evaluating Danish Models.
-
EuroEval Leaderboard
📊8The robust European language model benchmark.
-
ScandEval: A Benchmark for Scandinavian Natural Language Processing
Paper • 2304.00906 • Published • 4 -
MTEB Leaderboard
📊7.64kEmbedding Leaderboard
-
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
Paper • 2406.02396 • Published • 1
These models constitute state-of-the-art models for Danish within their respective domain (highlighted below the model).
-
mistralai/Mistral-Small-3.1-24B-Instruct-2503
24B • Updated • 146k • 1.38k -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 451k • • 2.02k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 25.1k • • 920 -
google/gemma-2-9b-it
Text Generation • 9B • Updated • 674k • • 915