Merge branch 'main' into dolma_taggers

README.md

@@ -21,7 +21,7 @@ For more information please check out the following links:
 |                                                                                                         |                                                                                                         |
 | ------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
 | 📑 [**About**](https://centre-for-humanities-computing.github.io/danish-foundation-models/)              | A overview of the DFM project                                                                           |
-| [**Research Paper**](inreview)                                                                           | An paper introducing DFM and its rationale                                                              |
+| [**Research Paper**](https://arxiv.org/abs/2311.07264)                                                  | An paper introducing DFM and its rationale                                                              |
 | 🚀 [**Models**](https://centre-for-humanities-computing.github.io/danish-foundation-models/models_text/) | A overview of current models available through the DFM project                                          |
 | 💽 [**Datasets**](https://centre-for-humanities-computing.github.io/danish-foundation-models/dcc/)       | Includes datasheets about the datasets which includes preprocessing, reason for constructions and more. |
 

citation.cff

@@ -0,0 +1,57 @@
+cff-version: 1.2.0
+title: Danish Foundation Models
+message: >-
+  If you use this software or associated models, please cite
+  it as below.
+type: software
+authors:
+  - family-names: Enevoldsen
+    given-names: Kenneth
+  - family-names: Hansen
+    given-names: Lasse
+  - family-names: Nielsen
+    given-names: Dan S.
+  - family-names: Egebæk
+    given-names: Rasmus A. F.
+  - family-names: Holm
+    given-names: Søren V.
+  - family-names: Nielsen
+    given-names: Martin C.
+  - family-names: Bernstorff
+    given-names: Martin
+  - family-names: Larsen
+    given-names: Rasmus
+  - family-names: Jørgensen
+    given-names: Peter B.
+  - family-names: Højmark-Bertelsen
+    given-names: Malte
+  - family-names: Vahlstrup
+    given-names: Peter B.
+  - family-names: Møldrup-Dalum
+    given-names: Per
+  - family-names: Nielbo
+    given-names: Kristoffer
+identifiers:
+  - type: url
+    value: "https://arxiv.org/abs/2311.07264"
+repository-code: >-
+  https://github.com/centre-for-humanities-computing/danish-foundation-models
+url: >-
+  https://centre-for-humanities-computing.github.io/danish-foundation-models/
+abstract: >-
+  Large language models, sometimes referred to as foundation
+  models, have transformed multiple fields of research.
+  However, smaller languages risk falling behind due to high
+  training costs and small incentives for large companies to
+  train these models. To combat this, the Danish Foundation
+  Models project seeks to provide and maintain open,
+  well-documented, and high-quality foundation models for
+  the Danish language. This is achieved through broad
+  cooperation with public and private institutions, to
+  ensure high data quality and applicability of the trained
+  models. We present the motivation of the project, the
+  current status, and future perspectives.
+keywords:
+  - Danish
+  - natural language processing
+date-released: "2023-11-14"

docs/index.md

@@ -17,7 +17,7 @@ Welcome to the Danish Foundation Models (DFM) project, a pioneering initiative i
 3. To maintain a high standard of **documentation** of models such as model cards \[[Mitchell et al., 2019](https://arxiv.org/abs/1810.03993)\] and datasheets \[[Gebru et al., 2021](https://cacm.acm.org/magazines/2021/12/256932-datasheets-for-datasets/abstract)\].
 4. To **open-source** not only the models but also all components required for reproducibility such as pre-processing, training, and validation code.
 
-You can read more about the argument for Danish Language models in our [publication](inreview).
+You can read more about the argument for Danish Language models in our [publication](https://arxiv.org/abs/2311.07264).
 
 
 ##  Open-source models on closed-source data