Add pipeline tag, library name and link to paper

README.md

@@ -1,17 +1,21 @@
 ---
-license: apache-2.0
-language:
-- en
-- fi
 base_model:
 - LumiOpen/Poro-34B
 datasets:
 - sablo/oasst2_curated
 - LumiOpen/instruction-collection-fin
+language:
+- en
+- fi
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
 This is an SFT-tuned model of [Poro-34B](https://huggingface.co/LumiOpen/Poro-34B) with English and Finnish data. We trained this model as part of our experiments on the impact of multilingual instruction-tuning on Poro-34B. For a better chat experience, we recommend using [Poro-34B-chat](https://huggingface.co/LumiOpen/Poro-34B-chat) instead.
 
+The model was presented in the paper [Poro 34B and the Blessing of Multilinguality](https://huggingface.co/papers/2404.01856).
+
 ## Datasets
 
 ### SFT
@@ -90,7 +94,6 @@ seed: 42
 warmup_ratio: 0.1
 ```
 
-
 ## Evaluation
 
 We use [IFEval](https://huggingface.co/datasets/google/IFEval) to evaluate the performance of the model in English. For Finnish, we translated the IFEval prompts to [Finnish](https://huggingface.co/datasets/LumiOpen/ifeval_mt) with DeepL. We report the instruction-level strict accuracy: