Update README.md

README.md

@@ -10,21 +10,37 @@ datasets:
 - LumiOpen/instruction-collection-fin
 ---
 
-This is an SFT-tuned model of [Poro-34B](https://huggingface.co/LumiOpen/Poro-34B) with English and Finnish data. 
+This is an SFT-tuned model of [Poro-34B](https://huggingface.co/LumiOpen/Poro-34B) with English and Finnish data. We trained this model for experiments on the impact of multilingual instruction-tuning. For a better chat experience, we recommend using [Poro-34B-chat](https://huggingface.co/LumiOpen/Poro-34B-chat) instead.
 
-We use a curated subset of Open Assistant 2 and translated the dataset into Finnish using Poro-34B. We trained this model for experiments on the impact of multilingual instruction-tuning. For a better chat experience, we recommend using [Poro-34B-chat](https://huggingface.co/LumiOpen/Poro-34B-chat) instead.
+## Datasets
 
-**Datasets**
+**SFT**
 
-**Recipes**
+We use a curated subset of Open Assistant 2 and translated the dataset into Finnish using Poro-34B.
 
+**English OASST2**
+- [oasst2_curated](https://huggingface.co/datasets/sablo/oasst2_curated)
 
+**Finnish OASST2**
+- [instruction-collection-fin](https://huggingface.co/datasets/LumiOpen/instruction-collection-fin) (oasst2 subset)
 
-**Evaluation**
-TBA
+**DPO**
 
 
-**Citation**
+## Recipes
+
+**SFT**
+
+**DPO**
+
+## Evaluation
+
+
+
+## Citation
+
+We discuss our experimental setup and results in our NoDaLiDa 2025 paper.
+
 ```
 @inproceedings{
 zosa2024got,